© 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. 4228
    Prev
    Next
    INDEX
    Explanations

    chemical elements or compounds, specifically those ending in 'ate' or 'one'

    oai_token-act-pair · gpt-3.5-turbo

    segments related to specific scientific terminology or classifications

    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
    TextColor
    -0.75
    çīĪ
    -0.69
    coat
    -0.68
     lashes
    -0.67
    è£
    -0.66
     belts
    -0.66
     Polo
    -0.64
    ItemImage
    -0.63
    EVA
    -0.63
     lash
    -0.62
    POSITIVE LOGITS
    irlf
    0.84
    ertain
    0.81
    agine
    0.81
    vironment
    0.79
    uss
    0.78
    oir
    0.77
    urn
    0.77
    ellectual
    0.74
    ront
    0.73
    ieth
    0.72
    Activations Density 0.142%

    No Known Activations