© 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. 4574
    Prev
    Next
    INDEX
    Explanations

    words related to making an impact or leaving a strong impression

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "impression."

    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
    atts
    -0.78
    vez
    -0.72
    efer
    -0.67
    annis
    -0.64
     hips
    -0.61
    nect
    -0.61
     gestation
    -0.61
    practice
    -0.60
     retreat
    -0.60
     annex
    -0.59
    POSITIVE LOGITS
     impression
    1.06
     impressions
    0.92
    eless
    0.88
    istic
    0.84
    eful
    0.81
    able
    0.74
    izable
    0.72
    ı
    0.72
    tale
    0.69
    wcsstore
    0.68
    Activations Density 0.038%

    No Known Activations