INDEX

Explanations

interrogative sentences related to specific events or actions

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

 reluct

-1.76

 shenan

-1.72

 scrat

-1.71

 increa

-1.70

 impra

-1.69

 disagre

-1.65

 maneu

-1.65

 disreg

-1.63

 tolerably

-1.62

 cushi

-1.59

POSITIVE LOGITS

Literat

0.95

 minimalis

0.94

 höl

0.92

Horário

0.91

Dès

0.80

Etimo

0.80

Composição

0.80

Pró

0.79

 kosme

0.79

Até

0.77

Activations Density 0.060%

interrogative sentences related to specific events or actions

No Comments

No Known Activations