© 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. 4-RES-JB
    11. 19605
    Prev
    Next
    INDEX
    Explanations

    statements or phrases conveying a particular message or communication

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conveying a message

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

    No Comments

    Negative Logits
    essors
    -0.72
    ords
    -0.72
    pmwiki
    -0.70
    cons
    -0.69
    ENCY
    -0.67
    agonists
    -0.66
    ancies
    -0.66
    thens
    -0.65
    urses
    -0.64
    enses
    -0.64
    POSITIVE LOGITS
     message
    1.21
     messages
    1.08
    message
    1.01
     Messages
    0.98
     Message
    0.94
    FontSize
    0.91
    Message
    0.86
     goodbye
    0.82
    posts
    0.80
     conveyed
    0.79
    Activations Density 0.021%

    No Known Activations