© 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. 4695
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or commands

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions and their consequences

    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
    yssey
    -0.68
    oult
    -0.63
     respectively
    -0.57
    aukee
    -0.52
    anwhile
    -0.52
     actionGroup
    -0.51
    worth
    -0.50
    ishers
    -0.50
    These
    -0.50
    cells
    -0.50
    POSITIVE LOGITS
     it
    1.67
     thereof
    1.07
     It
    1.00
     thereto
    0.93
     therein
    0.92
    It
    0.91
    it
    0.91
     hers
    0.90
     theirs
    0.88
    Its
    0.79
    Activations Density 2.605%

    No Known Activations