© 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. 4-RES-JB
    6. 13212
    Prev
    Next
    INDEX
    Explanations

    mentions of recording studios

    oai_token-act-pair · gpt-3.5-turbo

    references to recording studios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avez
    -0.74
    isms
    -0.66
    pend
    -0.64
    andum
    -0.61
    MpServer
    -0.60
    reads
    -0.59
    ysics
    -0.58
     refere
    -0.58
     Blackwell
    -0.58
    mere
    -0.58
    POSITIVE LOGITS
     studio
    1.03
     studios
    0.88
    ctor
    0.81
    smanship
    0.75
     mog
    0.74
    hesda
    0.71
    orpor
    0.71
     mates
    0.70
    cle
    0.70
     apartment
    0.70
    Activations Density 0.021%

    No Known Activations