© 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. 8-RES-JB
    11. 109
    Prev
    Next
    INDEX
    Explanations

    quantitative and statistical information related to various categories such as crime rates, income levels, tax rates, and temperature averages

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" and other similar prepositions indicating location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REF
    -0.73
     fate
    -0.73
    unity
    -0.71
    pard
    -0.71
     ingred
    -0.70
    HAEL
    -0.67
    skin
    -0.67
    ŀ
    -0.67
    ĺħ
    -0.66
     convol
    -0.64
    POSITIVE LOGITS
     accordance
    1.26
    effic
    1.16
     relation
    1.15
    efficiency
    1.09
     spite
    1.09
     lieu
    1.09
    versions
    1.07
     comparison
    1.06
     conjunction
    1.01
    versely
    1.01
    Activations Density 0.328%

    No Known Activations