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. 4749
    Prev
    Next
    INDEX
    Explanations

    verbs related to significant actions taken by individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    actions related to legal, political, or contentious events

    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
     âĶľâĶĢâĶĢ
    -0.72
    ivable
    -0.69
    respective
    -0.65
    iner
    -0.63
    ahime
    -0.61
    inen
    -0.60
     âĶľ
    -0.60
    dds
    -0.59
     ILCS
    -0.59
    ccording
    -0.58
    POSITIVE LOGITS
     theirs
    0.90
     hers
    0.76
     unexpectedly
    0.74
     unsuccessfully
    0.71
     him
    0.70
     them
    0.67
     prematurely
    0.64
     Schwe
    0.64
     mysteriously
    0.63
     abruptly
    0.62
    Activations Density 0.433%

    No Known Activations