INDEX

Explanations

mentions of specific names, especially related to political scandals

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ké

-0.53

lift

-0.52



-0.49

uatu

-0.49

Ralph

-0.47

Cos

-0.47

 Ralph

-0.47

Sheffield

-0.43

Marvel

-0.43

Cos

-0.42

POSITIVE LOGITS

 steven

0.96

 STEVEN

0.88

 Nixon

0.88

steven

0.81

Nixon

0.78

 Steven

0.74

Steven

0.73

 Whence

0.70

 Stevenson

0.66

 pavillon

0.66

Activations Density 0.275%

mentions of specific names, especially related to political scandals

No Comments

No Known Activations