© 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. 3-RES-JB
    6. 12085
    Prev
    Next
    INDEX
    Explanations

    pronouns 'it' and references to public announcements

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" in various contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anarchy
    -0.69
     Bian
    -0.69
     Earthqu
    -0.67
     Vict
    -0.65
     Friend
    -0.65
     Orn
    -0.63
     Anat
    -0.62
    stories
    -0.61
     Deaths
    -0.61
     Di
    -0.60
    POSITIVE LOGITS
    self
    1.09
    unes
    1.04
    chy
    1.01
    alian
    0.99
    zbollah
    0.96
    asca
    0.93
    hers
    0.92
    ueller
    0.85
    henko
    0.84
    cair
    0.82
    Activations Density 0.528%

    No Known Activations