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. 8884
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change in topic or a transition in a conversation

    oai_token-act-pair · gpt-3.5-turbo

    the word "anyway" and its variations, indicating a shift in conversation or topic

    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
     solitary
    -0.69
    prus
    -0.65
     brig
    -0.63
     prost
    -0.63
    adr
    -0.62
    ©¶æ
    -0.60
    urg
    -0.59
     crucifix
    -0.58
     centerpiece
    -0.56
    negie
    -0.55
    POSITIVE LOGITS
     Anyway
    0.94
     anyways
    0.89
    ional
    0.83
     anyway
    0.82
    Anyway
    0.80
     gotta
    0.75
    forth
    0.74
    ipop
    0.74
    hey
    0.73
    leep
    0.73
    Activations Density 0.022%

    No Known Activations