© 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. 3-RES-JB
    11. 10752
    Prev
    Next
    INDEX
    Explanations

    words related to hiding or concealing

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or states of being, particularly those associated with responsibility or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.70
    omez
    -0.63
    aughtered
    -0.61
    enhagen
    -0.60
    dl
    -0.59
    ources
    -0.58
    ensen
    -0.58
    ahime
    -0.58
    umbn
    -0.57
    thia
    -0.56
    POSITIVE LOGITS
    pillar
    0.75
    lehem
    0.74
    levard
    0.72
    halla
    0.68
    ĪĴ
    0.67
    apest
    0.67
    artisan
    0.64
     Commando
    0.64
    abase
    0.64
     Haram
    0.64
    Activations Density 0.106%

    No Known Activations