© 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. 7-RES-JB
    11. 13445
    Prev
    Next
    INDEX
    Explanations

    adjective phrases used to describe something or someone

    oai_token-act-pair · gpt-3.5-turbo

    descriptions or evaluations of various subjects or entities

    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
    ersen
    -0.77
    utical
    -0.71
    Side
    -0.69
    bucks
    -0.67
    iership
    -0.65
    rone
    -0.63
    IELD
    -0.62
    OTAL
    -0.60
    RL
    -0.60
    EA
    -0.59
    POSITIVE LOGITS
     "âĢ¦
    1.00
     "...
    1.00
     follows
    0.98
     "
    0.89
     "'
    0.85
     having
    0.82
     "[
    0.82
     well
    0.80
    pires
    0.76
     being
    0.76
    Activations Density 0.071%

    No Known Activations