Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 21838
    Prev
    Next
    INDEX
    Explanations

    mentions of technical details or features in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    cognitive functions or topics related to awareness and consciousness

    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
    }}
    -0.59
    }.
    -0.57
    )).
    -0.56
    ]).
    -0.55
    SPONSORED
    -0.55
    Ħ¢
    -0.53
    })
    -0.52
    ''.
    -0.49
    .</
    -0.48
    ].
    -0.48
    POSITIVE LOGITS
    undrum
    0.47
    iquid
    0.45
    veland
    0.43
    arij
    0.42
     awa
    0.41
    surprisingly
    0.41
    anchester
    0.41
    ependent
    0.40
    endum
    0.40
    orno
    0.40
    Activations Density 4.467%

    No Known Activations