Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 12535
    Prev
    Next
    INDEX
    Explanations

    references to diverse topics such as skin, genetics, and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological characteristics and physical attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tours
    -0.69
     announcements
    -0.68
     Tours
    -0.67
     lectures
    -0.65
     instruction
    -0.61
     Announce
    -0.58
     Instruct
    -0.58
     Opera
    -0.57
     speeches
    -0.57
     seminars
    -0.57
    POSITIVE LOGITS
    ãĥĺãĥ©
    0.82
    ebted
    0.75
     remnant
    0.74
     leftover
    0.73
     shrunk
    0.71
    orph
    0.71
    urden
    0.71
    tiny
    0.70
    shr
    0.70
     residual
    0.68
    Activations Density 1.351%

    No Known Activations