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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 18772
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluations or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    expressions of entitlement or perceived deservingness

    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
     appointments
    -0.82
     subordinates
    -0.75
    weights
    -0.74
     volunteers
    -0.70
     attendees
    -0.70
     developments
    -0.70
     events
    -0.69
     tweets
    -0.69
     fellows
    -0.68
     inquiries
    -0.68
    POSITIVE LOGITS
    versive
    1.19
     variety
    1.13
     plethora
    1.06
     lot
    1.03
     disproportionate
    0.98
     multitude
    0.97
     tendency
    0.97
    uras
    0.95
     glimpse
    0.92
    rouse
    0.92
    Activations Density 0.473%

    No Known Activations