INDEX

Explanations

terms related to political figures, statements, and 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 impra

-1.88

 disagre

-1.88

 increa

-1.85

 reluct

-1.82

 maneu

-1.79

 inev

-1.75

 uninten

-1.75

 encomp

-1.71

 disreg

-1.69

 tolerably

-1.69

POSITIVE LOGITS

“

1.06

0.99

«

0.94

“

0.82

„

0.81

 “[

0.79

"[

0.77

"'

0.74

「

0.72

”

0.70

Activations Density 0.953%

terms related to political figures, statements, and actions

No Comments

No Known Activations