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. 19065
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and military conflicts, especially those involving specific entities or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to significant historical events or conflicts

    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
     confir
    -0.65
    abad
    -0.59
     nutshell
    -0.57
     largeDownload
    -0.55
     à¨
    -0.53
     interviewed
    -0.53
     consists
    -0.51
     refers
    -0.51
     Edited
    -0.50
     denotes
    -0.50
    POSITIVE LOGITS
    )).
    0.83
    onto
    0.82
    ]."
    0.70
    ]).
    0.63
    '."
    0.63
    .'"
    0.62
    $.
    0.62
    %.
    0.59
    sic
    0.59
    icit
    0.58
    Activations Density 1.657%

    No Known Activations