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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-RES-JB
    6. 9445
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "gave" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gave."

    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
    ansas
    -0.71
    {{
    -0.67
    ?????-
    -0.66
    Page
    -0.66
    Chall
    -0.66
    IA
    -0.65
    Die
    -0.64
    âĸ¬
    -0.63
    lihood
    -0.63
    Cache
    -0.61
    POSITIVE LOGITS
    aways
    0.89
     rise
    0.76
     precedence
    0.75
     Pwr
    0.73
     generously
    0.73
    itial
    0.73
     birth
    0.72
    giving
    0.72
     them
    0.69
     us
    0.68
    Activations Density 0.045%

    No Known Activations