INDEX

Explanations

long, specific names and terms, potentially including surnames and locations

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

epsfig

-0.55

lüğ

-0.55

 vsak

-0.52

leyeb

-0.52

ceğim

-0.52

 oseb

-0.52

lenmiş

-0.52

ceğini

-0.51

 Septembre

-0.51

ceğ

-0.49

POSITIVE LOGITS

 kele

0.89

 seksi

0.88

 sula

0.88

 lele

0.85

 antik

0.85

 ille

0.84

 maksi

0.84

 kosme

0.84

 silikon

0.84

 kollek

0.84

Activations Density 0.298%

long, specific names and terms, potentially including surnames and locations

No Comments

No Known Activations