© 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. 2-RES-JB
    11. 19849
    Prev
    Next
    INDEX
    Explanations

    phrases related to consistency

    oai_token-act-pair · gpt-3.5-turbo

    repetitive references to consistent actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.94
    ster
    -0.78
    lda
    -0.75
    atorium
    -0.73
    lyss
    -0.67
    ogens
    -0.67
    soc
    -0.67
    OTA
    -0.65
    hemy
    -0.65
    rison
    -0.65
    POSITIVE LOGITS
     conclud
    0.88
     conduc
    0.86
    uously
    0.84
     strugg
    0.82
    ciating
    0.81
    ©¶æ¥µ
    0.78
     deterior
    0.77
     evolve
    0.76
     exhibited
    0.75
     behaved
    0.75
    Activations Density 0.007%

    No Known Activations