© 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. 9-RES-JB
    11. 15626
    Prev
    Next
    INDEX
    Explanations

    actions related to data processing and transmission

    oai_token-act-pair · gpt-3.5-turbo

    actions related to data transmission and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ooters
    -0.70
    icult
    -0.68
    ooter
    -0.61
     Cosponsors
    -0.60
    pac
    -0.58
    nia
    -0.56
    antis
    -0.55
    pmwiki
    -0.55
    ieth
    -0.53
    hetti
    -0.53
    POSITIVE LOGITS
     them
    1.26
     accordingly
    1.22
     therein
    1.04
     thereto
    0.96
     thereof
    0.93
     it
    0.92
    them
    0.91
     THEM
    0.89
     thereafter
    0.87
     resultant
    0.82
    Activations Density 0.426%

    No Known Activations