© 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. 4-RES-JB
    11. 15274
    Prev
    Next
    INDEX
    Explanations

    phrases related to survey or research organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to "Forum" as an organization or context

    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
    kowski
    -0.70
    mia
    -0.64
    yrights
    -0.64
    ymes
    -0.61
    teenth
    -0.61
    cano
    -0.60
    tics
    -0.58
    chen
    -0.57
    lys
    -0.57
     biologically
    -0.57
    POSITIVE LOGITS
    ioned
    0.83
    area
    0.77
    naire
    0.77
    edIn
    0.77
    dayName
    0.74
    ilitation
    0.74
     forum
    0.73
     Forum
    0.69
    ative
    0.67
    ãĥ¼ãĥĨãĤ£
    0.67
    Activations Density 0.013%

    No Known Activations