© 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. 4-RES-JB
    11. 6566
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "nut" or variations of "nut" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to walnuts and related terms

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

    No Comments

    Negative Logits
    Ĥİ
    -0.81
    ngth
    -0.70
     bargaining
    -0.66
    relative
    -0.64
     transient
    -0.63
    hovah
    -0.62
    Transfer
    -0.62
    absolute
    -0.62
     pronouns
    -0.61
    activated
    -0.61
    POSITIVE LOGITS
    rient
    1.05
    rients
    0.95
    ritional
    0.83
    rition
    0.82
    elia
    0.80
    nut
    0.80
    stein
    0.79
    ridge
    0.77
    wo
    0.77
    ãĥ³ãĤ¸
    0.74
    Activations Density 0.016%

    No Known Activations