© 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. 6-RES-JB
    11. 7905
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or changes happening to something

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases indicating support or compensatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !,
    -0.50
    ngth
    -0.49
    !/
    -0.46
     thriller
    -0.46
    Ħ¢
    -0.46
     Beautiful
    -0.45
     Spotlight
    -0.45
    !.
    -0.44
     worldwide
    -0.43
     POLITICO
    -0.43
    POSITIVE LOGITS
    kees
    0.57
    rin
    0.55
    arat
    0.50
    chal
    0.48
    ãĥĹ
    0.47
    eenth
    0.46
    ying
    0.46
    rd
    0.45
    fitting
    0.44
    aran
    0.44
    Activations Density 0.822%

    No Known Activations