© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 4467
    Prev
    Next
    INDEX
    Explanations

    words related to opposing forces or challenges

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resistance" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.80
    monds
    -0.71
    cester
    -0.70
    ogg
    -0.69
    orp
    -0.69
    oufl
    -0.68
    estone
    -0.68
    utters
    -0.67
    =-=-=-=-
    -0.67
    uras
    -0.67
    POSITIVE LOGITS
     resistance
    1.24
     Resistance
    0.96
     resistant
    0.79
     fighters
    0.76
    istance
    0.76
     dictate
    0.75
     regimes
    0.74
     thereto
    0.74
    ngth
    0.73
    xual
    0.72
    Activations Density 0.009%

    No Known Activations