INDEX

Explanations

names of specific individuals

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

Flere

-0.84

 Kruse

-0.70

elegante

-0.65

Hvordan

-0.65

Hvem

-0.65

 Hermans

-0.62

 Schreiber

-0.58

Hvorfor

-0.57

Hvor

-0.57

 Schröder

-0.56

POSITIVE LOGITS

 stopp

0.90

 paff

0.89

udd

0.81

 bandung

0.81

 noss

0.78

 tass

0.78

obb

0.78

 Krzysz

0.78

 fupp

0.77

 milano

0.77

Activations Density 0.411%

names of specific individuals

No Comments

No Known Activations