© 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. 15139
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "dined" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the verb "dine" and its related variations

    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
    Reviewer
    -0.65
    ħĭ
    -0.63
    say
    -0.61
    endif
    -0.60
    isphere
    -0.60
    Translation
    -0.59
    src
    -0.58
    OTHER
    -0.58
    ãĥŁ
    -0.58
    SpaceEngineers
    -0.58
    POSITIVE LOGITS
    tails
    0.76
     buggy
    0.74
    rolet
    0.71
    bag
    0.70
    legged
    0.68
    ennes
    0.68
    odge
    0.67
     acquaint
    0.66
     Restaur
    0.66
    tail
    0.65
    Activations Density 0.099%

    No Known Activations