Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22813
    Prev
    Next
    INDEX
    Explanations

    phrases indicating improvement or comparison between different options

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express being "better off" in various contexts

    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
    FK
    -0.71
    cru
    -0.66
    ART
    -0.66
     inacc
    -0.65
    ologic
    -0.64
    forestation
    -0.64
    Saint
    -0.63
     flare
    -0.63
    AX
    -0.61
    Cl
    -0.61
    POSITIVE LOGITS
     financially
    0.94
     investing
    0.82
     than
    0.76
    looking
    0.76
     renting
    0.76
     footing
    0.76
     reacting
    0.73
     knowing
    0.71
     bets
    0.70
     buying
    0.69
    Activations Density 0.052%

    No Known Activations