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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 1179
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a transition or change of some sort

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate transformation or progression towards a new state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ailability
    -0.72
    ©¶æ
    -0.65
    rouse
    -0.65
     blinded
    -0.63
     trained
    -0.62
     cowork
    -0.62
     Canterbury
    -0.61
     towed
    -0.60
     forefront
    -0.60
     Buckingham
    -0.60
    POSITIVE LOGITS
    thood
    0.75
    ãģ¦
    0.71
    ENCE
    0.71
    actionDate
    0.70
    encia
    0.70
    ptive
    0.69
    bert
    0.67
    earing
    0.67
    tons
    0.67
    ptoms
    0.66
    Activations Density 0.041%

    No Known Activations