INDEX

Explanations

descriptions related to locations or events

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

 schal

-0.85

Lma

-0.79

Væ

-0.78

År

-0.75

Noice

-0.75

Lmfao

-0.75

Vå

-0.72

Gå

-0.70

 sako

-0.69

Ikr

-0.69

POSITIVE LOGITS

Sklici

0.65

 ***!

0.61

Zunanje

0.60

 whither

0.59

AndEndTag

0.57

bitField

0.57

 Located

0.57

ConstraintMaker

0.56

 There

0.55

 Where

0.55

Activations Density 0.732%

descriptions related to locations or events

No Comments

No Known Activations