© 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. 0-RES-JB
    11. 16560
    Prev
    Next
    INDEX
    Explanations

    terms related to assisting or aiding someone

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "assisted" and related terms indicating help or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lash
    -0.99
     crumble
    -0.67
    gram
    -0.67
    ieties
    -0.67
    daq
    -0.63
     Saban
    -0.62
    px
    -0.62
    @#
    -0.61
    ãĤ§
    -0.60
    igm
    -0.59
    POSITIVE LOGITS
     assisted
    3.96
    assisted
    2.58
     aided
    2.29
     facilitated
    1.60
     assisting
    1.55
     supervised
    1.50
     assist
    1.50
     Assist
    1.41
     assists
    1.31
     induced
    1.30
    Activations Density 0.013%

    No Known Activations