© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16077
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the best or most suitable options in a given context

    oai_token-act-pair · gpt-3.5-turbo

    important aspects related to notifications and communication in contexts like emails and alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ©ãĥ³
    -0.69
     Claims
    -0.67
    igious
    -0.66
    ¶ħ
    -0.63
    quartered
    -0.62
     bombard
    -0.60
    thood
    -0.60
    esta
    -0.58
    ãĤ©
    -0.58
     Reporting
    -0.57
    POSITIVE LOGITS
     preferable
    1.68
     advisable
    1.53
     optimal
    1.44
     appropriate
    1.38
     desirable
    1.31
     prudent
    1.30
     suitable
    1.30
     feasible
    1.29
     optimum
    1.28
     acceptable
    1.26
    Activations Density 0.515%

    No Known Activations