© 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. 260
    Prev
    Next
    INDEX
    Explanations

    unusual symbols or characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or uncommon symbols in the text

    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
     KH
    -0.41
    ciplinary
    -0.40
     nutshell
    -0.40
    ©¶æ
    -0.39
     Media
    -0.38
     Garry
    -0.38
     Mell
    -0.38
     fielder
    -0.38
     row
    -0.38
     vill
    -0.38
    POSITIVE LOGITS
    sic
    0.70
    emphasis
    0.64
    their
    0.64
    $$$$
    0.61
    rather
    0.59
    something
    0.58
    ONSORED
    0.58
    instead
    0.57
    meaning
    0.57
    they
    0.57
    Activations Density 0.730%

    No Known Activations