© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6016
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "It" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "It is" or similar constructions that introduce a statement or explanation

    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
     �
    -0.71
    ?).
    -0.62
     ''
    -0.61
     β
    -0.60
     prompting
    -0.59
    .)
    -0.58
    .).
    -0.58
     Gohan
    -0.57
     guiActiveUnfocused
    -0.57
     respectively
    -0.55
    POSITIVE LOGITS
    %"
    1.06
    withstanding
    1.05
    ntil
    0.96
    pherd
    0.88
    "—
    0.87
    "[
    0.86
    odore
    0.85
    ":
    0.85
    ,"
    0.85
    ircraft
    0.84
    Activations Density 0.288%

    No Known Activations