© 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. 2-RES-JB
    11. 1982
    Prev
    Next
    INDEX
    Explanations

    phrases related to passing information from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "forwarded" and related terms associated with email or message forwarding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cular
    -0.79
    teenth
    -0.76
    akening
    -0.70
    aver
    -0.68
    avid
    -0.68
    arta
    -0.67
    tics
    -0.66
    isan
    -0.66
    arij
    -0.65
    arcity
    -0.65
    POSITIVE LOGITS
     forwarded
    1.20
     forwarding
    1.12
    forward
    0.88
    geist
    0.82
     RFC
    0.76
    Forward
    0.72
     replies
    0.71
     emails
    0.69
    folios
    0.66
     Forward
    0.65
    Activations Density 0.015%

    No Known Activations