© 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. 4655
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting or opposing ideas

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used frequently in various contexts

    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
    ahime
    -0.83
    hart
    -0.78
    ":-
    -0.73
    ciples
    -0.71
     Flags
    -0.67
    igr
    -0.67
    acas
    -0.66
    oused
    -0.65
    Sep
    -0.65
    ributes
    -0.64
    POSITIVE LOGITS
     rightfully
    1.21
     vice
    1.19
     indeed
    1.18
     hence
    1.15
     rightly
    1.12
     consequently
    1.09
     thus
    1.08
     possibly
    1.07
     therefore
    1.04
     doubtless
    1.04
    Activations Density 0.101%

    No Known Activations