© 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. 17726
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "hammer" with varying levels of relevance and context

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "hammer" and its variations in the text

    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
    VICE
    -0.72
    RIP
    -0.69
    ected
    -0.68
    ection
    -0.66
    ITIES
    -0.66
     Matter
    -0.66
    uce
    -0.65
    say
    -0.65
    Leary
    -0.64
     Leaders
    -0.64
    POSITIVE LOGITS
     hammer
    1.23
    sonian
    0.99
     hammered
    0.98
    hammer
    0.96
    bats
    0.94
     hamm
    0.93
    matical
    0.86
     nails
    0.85
    eer
    0.80
     wrench
    0.79
    Activations Density 0.011%

    No Known Activations