© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3293
    Prev
    Next
    INDEX
    Explanations

    words related to phishing or misleading activities

    oai_token-act-pair · gpt-3.5-turbo

    words related to phobia or fear

    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
    éĹĺ
    -0.87
    HCR
    -0.85
    CLASSIFIED
    -0.71
    TRY
    -0.68
     Paw
    -0.65
     Horror
    -0.64
     Arabia
    -0.64
     Pitch
    -0.64
    PRES
    -0.64
     Hussein
    -0.64
    POSITIVE LOGITS
    oenix
    1.46
    ilipp
    1.18
    allic
    1.17
    araoh
    1.12
    oning
    1.12
    antom
    1.11
    ysics
    1.10
    obia
    1.09
    agons
    1.08
    oned
    1.03
    Activations Density 0.030%

    No Known Activations