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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5148
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases indicating a desire or need to communicate with others

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating direct communication or interaction

    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
    Released
    -0.68
     doubtless
    -0.64
     reprinted
    -0.58
    imov
    -0.58
    CHO
    -0.56
    hler
    -0.55
     debuted
    -0.55
     fielded
    -0.54
    cember
    -0.54
     compounded
    -0.54
    POSITIVE LOGITS
     oneself
    0.92
     anything
    0.81
    ordinate
    0.69
     Yourself
    0.66
    anything
    0.65
     whichever
    0.65
     any
    0.64
     whatever
    0.64
     your
    0.63
     something
    0.63
    Activations Density 0.572%

    No Known Activations