INDEX

Explanations

phrases or terms related to specific topics or themes

oai_token-act-pair · gpt-3.5-turbo

the variable phrase 'Ļ' across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Not in Any Lists

No Comments

Negative Logits

ITNESS

-0.64

 seiz

-0.63

 sacrific

-0.62

 Negro

-0.61

 Afric

-0.61

ĵĺ

-0.61

 unden

-0.60

 SERV

-0.59

 STATES

-0.59

achus

-0.59

POSITIVE LOGITS

ï¸ı

1.33

esc

0.86

Â£

0.78

0.76

ti

0.74

TION

0.74

ãĤĭ

0.72

ery

0.71

eric

0.70

è£

0.70

Activations Density 0.189%

phrases or terms related to specific topics or themes

the variable phrase 'Ļ' across various contexts

No Comments

No Known Activations