© 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. 9-RES-JB
    11. 1631
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    date information

    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
    ancial
    -0.62
    luent
    -0.60
    phabet
    -0.60
    avorite
    -0.59
     likeness
    -0.59
    osponsors
    -0.58
     Clapper
    -0.56
    ophone
    -0.55
     Cantor
    -0.55
    igon
    -0.54
    POSITIVE LOGITS
    å¹
    0.81
    cember
    0.80
    ober
    0.75
    ember
    0.72
    ASON
    0.70
    28
    0.69
    aug
    0.68
    01
    0.68
    2200
    0.67
     08
    0.67
    Activations Density 0.046%

    No Known Activations