© 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. 3-RES-JB
    11. 22769
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'hound'

    oai_token-act-pair · gpt-3.5-turbo

    words that include the substring "ound."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skelet
    -0.92
    perty
    -0.76
    uters
    -0.68
     exha
    -0.67
    utations
    -0.66
    utic
    -0.66
    etheus
    -0.66
    女
    -0.64
    apons
    -0.63
     toget
    -0.63
    POSITIVE LOGITS
    ertain
    0.79
    rums
    0.77
    oslav
    0.75
    Sound
    0.75
    weight
    0.74
    ãĥĥãĥĪ
    0.72
    witz
    0.69
    lords
    0.69
    ers
    0.69
    arthed
    0.69
    Activations Density 0.007%

    No Known Activations