© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 1327
    Prev
    Next
    INDEX
    Explanations

    phrases related to negotiations or agreements

    oai_token-act-pair · gpt-3.5-turbo

    commas and other punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertain
    -0.84
    hov
    -0.84
    scribe
    -0.71
    uce
    -0.71
    inar
    -0.66
     Activities
    -0.62
    è£ħ
    -0.61
    elf
    -0.59
    iven
    -0.59
    yon
    -0.59
    POSITIVE LOGITS
     albeit
    1.18
     citing
    1.15
     noting
    1.05
     stating
    1.00
     namely
    0.98
     though
    0.98
     saying
    0.97
     preferring
    0.96
     although
    0.96
     however
    0.95
    Activations Density 0.330%

    No Known Activations