INDEX

Explanations

phrases related to sound effects or onomatopoeic words

oai_token-act-pair · gpt-3.5-turbo

references to song titles or popular musical phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•Misc

repeating token feature

No Comments

Negative Logits

Newsletter

-0.86

 seiz

-0.72

Untitled

-0.71

ãĥ´

-0.69

 guiActiveUn

-0.69

Īè

-0.65

zanne

-0.64

ãĥĩãĤ£

-0.63

emouth

-0.63

ï¸ı

-0.63

POSITIVE LOGITS

ingen

0.69

 Coyotes

0.68

 Kenobi

0.66

 Kinnikuman

0.65

IU

0.65

lar

0.64

 Rebels

0.64

OT

0.62

loo

0.58

 Wink

0.57

Activations Density 0.209%

phrases related to sound effects or onomatopoeic words

references to song titles or popular musical phrases

No Comments

No Known Activations