© 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. 8-RES-JB
    11. 4116
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with "It"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "It" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NX
    -0.64
     Opt
    -0.61
     Unlimited
    -0.58
     Hive
    -0.56
    opathic
    -0.56
     ART
    -0.56
     Incarnation
    -0.56
     heartbeat
    -0.56
     retiring
    -0.56
     Toast
    -0.56
    POSITIVE LOGITS
    zbollah
    1.05
     transpired
    1.01
    amar
    0.94
    unes
    0.89
     seems
    0.88
     emerged
    0.88
    iannopoulos
    0.87
     coincided
    0.87
    iner
    0.87
     occurred
    0.87
    Activations Density 0.220%

    No Known Activations