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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 3691
    Prev
    Next
    INDEX
    Explanations

    web URLs and commands related to running programs

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leaps
    -0.86
    ertodd
    -0.80
     densely
    -0.75
     veins
    -0.75
     pounding
    -0.74
     obser
    -0.74
     scattering
    -0.74
     verses
    -0.74
     writ
    -0.73
     bites
    -0.73
    POSITIVE LOGITS
    custom
    1.22
    example
    1.22
    default
    1.17
    local
    1.17
    foo
    1.16
    temp
    1.16
    true
    1.14
    global
    1.12
    new
    1.12
    shared
    1.12
    Activations Density 0.217%

    No Known Activations