© 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. 1-RES-JB
    11. 3200
    Prev
    Next
    INDEX
    Explanations

    phrases related to forming opinions or perspectives on something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "impression"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.72
     hips
    -0.69
    regulated
    -0.67
    yss
    -0.64
     planning
    -0.62
     legalized
    -0.62
     plotted
    -0.62
     intensive
    -0.61
     filing
    -0.61
    iding
    -0.61
    POSITIVE LOGITS
     impression
    1.41
     impressions
    1.22
    IELD
    0.79
    uren
    0.78
    -+-+
    0.75
    ROR
    0.74
     perceptions
    0.71
     Wiz
    0.71
    ãĥ¼ãĥĨ
    0.71
    RECT
    0.71
    Activations Density 0.006%

    No Known Activations