© 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. 7-RES-JB
    11. 22841
    Prev
    Next
    INDEX
    Explanations

    phrases related to various ways of doing things or taking action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to means and methods of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    livious
    -0.82
    head
    -0.81
    roth
    -0.70
    heads
    -0.65
    llah
    -0.64
     Roller
    -0.63
    clair
    -0.61
    rollment
    -0.60
    ATOR
    -0.60
    abad
    -0.59
    POSITIVE LOGITS
     practicable
    1.31
     possible
    1.24
     necessary
    1.20
     feasible
    1.12
     appropriate
    1.11
     desired
    1.10
    necessary
    1.06
     reasonably
    0.95
     imaginable
    0.93
     needed
    0.93
    Activations Density 0.524%

    No Known Activations