Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 16995
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person named "Hitz" and possibly some related phrases

    oai_token-act-pair · gpt-3.5-turbo

    compound or complex words

    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
     referen
    -0.70
     Moroc
    -0.57
     thous
    -0.55
     corrid
    -0.53
    ãĥ¼ãĥĨ
    -0.51
    ãĥ¼ãĥĨãĤ£
    -0.50
     CLSID
    -0.44
     Leilan
    -0.42
     Nicarag
    -0.42
     predec
    -0.42
    POSITIVE LOGITS
    NetMessage
    0.65
    othes
    0.50
    ank
    0.49
    SELECT
    0.49
    taboola
    0.49
    ANS
    0.47
    lement
    0.47
    posing
    0.47
    rov
    0.47
    iosis
    0.46
    Activations Density 2.785%

    No Known Activations