© 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. 8-RES-JB
    11. 15167
    Prev
    Next
    INDEX
    Explanations

    phrases related to importance, core, or significant aspects of topics being discussed

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the central or foundational components of various subjects or issues

    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
    osponsors
    -0.75
    ruciating
    -0.70
     RELEASE
    -0.67
    apon
    -0.65
    DERR
    -0.64
    byter
    -0.64
    orneys
    -0.63
    ufact
    -0.63
    intend
    -0.62
    apons
    -0.60
    POSITIVE LOGITS
     thereof
    0.88
    waters
    0.86
    most
    0.85
    strings
    0.76
    verse
    0.74
    mast
    0.72
    gro
    0.71
    Theme
    0.71
     of
    0.71
    plates
    0.69
    Activations Density 0.064%

    No Known Activations