© 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. 6-RES-JB
    11. 14825
    Prev
    Next
    INDEX
    Explanations

    adjectives related to quality or characteristics, particularly emphasizing unprocessed state or potential

    oai_token-act-pair · gpt-3.5-turbo

    references to "raw" materials or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itism
    -0.81
    ŃĶ
    -0.80
     Explain
    -0.79
    agall
    -0.76
    agements
    -0.76
    ommel
    -0.75
    uate
    -0.75
    ately
    -0.74
    uyomi
    -0.73
    onial
    -0.73
    POSITIVE LOGITS
    hide
    1.42
     sewage
    1.05
    lings
    1.03
    ls
    1.03
    esome
    0.98
    lins
    0.93
     materials
    0.90
     throats
    0.89
    blood
    0.84
    ted
    0.77
    Activations Density 0.019%

    No Known Activations