INDEX

Explanations

words related to power dynamics and societal issues, such as disenfranchisement, recalcitrance, and oppression

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

 effe

-1.83

 desir

-1.64

 lidl

-1.63

 dispen

-1.62

 erec

-1.62

ivi

-1.58

 igno

-1.56

 wien

-1.56

 noss

-1.55

 noel

-1.55

POSITIVE LOGITS

0.75

ment

0.74

0.71

ative

0.71

and

0.71

ments

0.71

ation

0.70

ous

0.68

ly

0.68

Activations Density 0.644%

words related to power dynamics and societal issues, such as disenfranchisement, recalcitrance, and oppression

No Comments

No Known Activations