© 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. 7669
    Prev
    Next
    INDEX
    Explanations

    words related to negative or critical opinions or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to denial

    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
    ramid
    -0.66
     Annotations
    -0.65
     Trooper
    -0.63
    lda
    -0.61
     Carbuncle
    -0.60
    committee
    -0.60
    LER
    -0.59
    EED
    -0.59
    intendent
    -0.58
     permitting
    -0.58
    POSITIVE LOGITS
    unci
    1.53
    unciation
    1.49
    izens
    1.45
    ounces
    1.20
    igration
    1.19
    uclear
    1.18
    izen
    1.15
    ormal
    1.15
    atural
    1.14
    igrated
    1.10
    Activations Density 0.016%

    No Known Activations