© 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. 6575
    Prev
    Next
    INDEX
    Explanations

    instances where someone or something is "also" related to a topic or action

    oai_token-act-pair · gpt-3.5-turbo

    the word "also" in various contexts

    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
    Leave
    -0.73
    stice
    -0.70
    iliate
    -0.67
    ASE
    -0.66
    jam
    -0.63
    anth
    -0.63
    Aren
    -0.62
     Intake
    -0.61
     Flames
    -0.60
    acious
    -0.59
    POSITIVE LOGITS
     noteworthy
    0.88
     priv
    0.88
     notable
    0.87
     known
    0.87
     incorporated
    0.78
     considered
    0.78
     included
    0.77
     susceptible
    0.74
     implicated
    0.74
    ŃĶ
    0.74
    Activations Density 0.063%

    No Known Activations