© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4635
    Prev
    Next
    INDEX
    Explanations

    settings or descriptions that convey a particular mood or atmosphere, often related to darkness or intensity

    oai_token-act-pair · gpt-3.5-turbo

    definite articles in various contexts within the text

    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
    olicy
    -0.94
    mania
    -0.72
    brate
    -0.72
    acca
    -0.69
    joice
    -0.67
    LEASE
    -0.65
    IPP
    -0.64
    Reason
    -0.64
    ulner
    -0.63
    rists
    -0.63
    POSITIVE LOGITS
     midst
    1.51
     doorway
    1.26
     hallway
    1.21
     middle
    1.13
     meantime
    1.12
     foreground
    1.11
     courtyard
    1.10
     vicinity
    1.09
     corner
    1.09
     attic
    1.02
    Activations Density 0.229%

    No Known Activations