© 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. 9-RES-JB
    11. 3594
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking something into consideration or including it in an analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the concept of considering or taking into account various factors or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rouse
    -0.84
    Ñı
    -0.83
    sis
    -0.77
    ciating
    -0.75
    ©¶æ¥µ
    -0.70
    Parser
    -0.67
    mid
    -0.67
    scribe
    -0.66
    Demon
    -0.66
    Kind
    -0.65
    POSITIVE LOGITS
     outl
    1.10
     factors
    1.07
     inflation
    1.04
     variables
    1.01
     covari
    0.98
     depreciation
    0.94
     confounding
    0.94
     rounding
    0.92
     probabilities
    0.90
     deductions
    0.90
    Activations Density 0.199%

    No Known Activations