© 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. 16230
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or people

    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
    ãĥ¼ãĥĨ
    -0.49
     CLSID
    -0.48
     referen
    -0.48
    ãĥ¼ãĥĨãĤ£
    -0.44
     Moroc
    -0.44
    VALUE
    -0.44
    acebook
    -0.41
    æ°
    -0.41
    ãĥĩãĤ£
    -0.41
     Titanic
    -0.40
    POSITIVE LOGITS
    NetMessage
    0.58
    amba
    0.48
    ANS
    0.47
    olin
    0.45
    amin
    0.45
    ifa
    0.44
    iosis
    0.44
    chem
    0.44
    ank
    0.42
    ip
    0.42
    Activations Density 2.042%

    No Known Activations