INDEX

Explanations

references to language proficiency and translation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.12.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.78

DockStyle

-0.71

+#+#

-0.66

isContained

-0.60

mapreduce

-0.59

íí

-0.58

bewerken

-0.57

setDo

-0.57

GORITH

-0.57

RuleContext

-0.57

POSITIVE LOGITS

 affor

1.53

 véhic

1.47

 maneu

1.43

 increa

1.40

Juf

1.35

 reluct

1.34

 accla

1.32

 beverly

1.32

 chrysler

1.32

 carrefour

1.30

Activations Density 0.298%

references to language proficiency and translation

No Comments

No Known Activations