© 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. 13193
    Prev
    Next
    INDEX
    Explanations

    terms related to "system" or "syndrome"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systems or systemic concepts

    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
    ORED
    -0.87
    DERR
    -0.84
    اÙĦ
    -0.79
     actionGroup
    -0.78
    éĹĺ
    -0.75
    ISION
    -0.71
     guiActiveUnfocused
    -0.71
    INGTON
    -0.70
    LESS
    -0.69
    âĵĺ
    -0.67
    POSITIVE LOGITS
     sy
    1.13
    philis
    1.11
    ringe
    1.06
    racuse
    0.94
    heter
    0.92
    lv
    0.85
    thia
    0.85
    seys
    0.83
    phthal
    0.82
    posium
    0.82
    Activations Density 0.007%

    No Known Activations