© 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. 3-RES-JB
    11. 15220
    Prev
    Next
    INDEX
    Explanations

    mentions of research organizations, specifically ones named "Forum"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Forum" as it relates to various studies, surveys, or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teenth
    -0.71
    yrights
    -0.69
    resp
    -0.67
    kowski
    -0.65
    imm
    -0.64
    mia
    -0.63
    tics
    -0.62
    adding
    -0.61
    teen
    -0.60
     skelet
    -0.59
    POSITIVE LOGITS
    edIn
    0.80
    naire
    0.80
     Forum
    0.79
    ilitation
    0.78
    ioned
    0.76
    dayName
    0.75
    urion
    0.70
     forum
    0.70
    ãĥ¼ãĥĨãĤ£
    0.69
    naires
    0.68
    Activations Density 0.005%

    No Known Activations