© 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. 18437
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to opportunities or competitiveness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "shot" and its variations

    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
     livest
    -0.81
    ŃĶ
    -0.70
    Reviewer
    -0.68
    accompanied
    -0.68
    Downloadha
    -0.68
    climate
    -0.67
    herty
    -0.65
    PRE
    -0.64
    LCS
    -0.64
    ensable
    -0.64
    POSITIVE LOGITS
    shot
    1.21
    gun
    0.92
    shots
    0.86
    nikov
    0.82
     Shot
    0.79
     revolver
    0.75
    ãĥĺ
    0.73
    guns
    0.72
     Rifle
    0.72
    lasses
    0.70
    Activations Density 0.007%

    No Known Activations