© 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
    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. 23577
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to news or information

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to personal relationships or experiences

    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
     Moroc
    -0.56
     referen
    -0.52
    ãĥ¼ãĥĨãĤ£
    -0.44
    edIn
    -0.44
    ãĥ¼ãĥĨ
    -0.43
    æµ
    -0.41
     CLSID
    -0.41
     [|
    -0.40
    acebook
    -0.40
    ilaterally
    -0.40
    POSITIVE LOGITS
     DRAGON
    0.44
    SELECT
    0.44
     largeDownload
    0.42
    merce
    0.41
    ANS
    0.40
     Shroud
    0.39
    rians
    0.39
    othes
    0.39
     SERV
    0.38
     DARK
    0.38
    Activations Density 4.774%

    No Known Activations