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. 7-RES-JB
    6. 4107
    Prev
    Next
    INDEX
    Explanations

    phrases related to certainty or belief, indicating possible doubt or validation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or truthfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.86
    izabeth
    -0.77
    afia
    -0.76
    umbnails
    -0.73
    elve
    -0.69
     hail
    -0.68
    quartered
    -0.68
    pick
    -0.64
     Slay
    -0.63
    ichever
    -0.63
    POSITIVE LOGITS
     happening
    1.16
     occurring
    0.87
     happen
    0.87
     happ
    0.86
    true
    0.82
     happened
    0.82
     untrue
    0.77
     accomplished
    0.77
     achievable
    0.76
     unintentional
    0.76
    Activations Density 0.300%

    No Known Activations