Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7419
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement or change of position

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating an action or participation in an event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rone
    -0.80
    zo
    -0.67
    âĹ¼
    -0.64
     Koreans
    -0.64
    ria
    -0.63
    ricular
    -0.60
     ignor
    -0.58
    rome
    -0.57
    ole
    -0.57
    street
    -0.56
    POSITIVE LOGITS
    hirt
    0.89
    paces
    0.88
    ometimes
    0.83
    atform
    0.82
    hift
    0.81
    ilver
    0.81
    omething
    0.77
    hement
    0.77
    anamo
    0.77
    psey
    0.75
    Activations Density 0.349%

    No Known Activations