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. 8097
    Prev
    Next
    INDEX
    Explanations

    successes or achievements

    oai_token-act-pair · gpt-3.5-turbo

    experiences of personal struggles and achievements

    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
    aic
    -0.65
    idates
    -0.62
     themselves
    -0.62
     Priebus
    -0.61
     Gad
    -0.61
    ocratic
    -0.61
     Lens
    -0.61
    odes
    -0.60
     Eisen
    -0.60
     Its
    -0.60
    POSITIVE LOGITS
     myself
    0.87
     thankful
    0.85
     fortunate
    0.80
     regret
    0.77
     conscious
    0.77
     skelet
    0.77
     grateful
    0.75
    heart
    0.74
     honestly
    0.73
     personally
    0.73
    Activations Density 0.488%

    No Known Activations