INDEX

Explanations

references to related topics or content as indicated by the "See also" labels

oai_token-act-pair · gpt-3.5-turbo

the phrase "see also"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ufact

-0.87

kefeller

-0.77

 Cree

-0.72

©¶æ¥µ

-0.70

eno

-0.68

VERSION

-0.66

bia

-0.65

ructose

-0.65

 Lifetime

-0.61

endi

-0.61

POSITIVE LOGITS

!:

0.81

...]

0.75

cart

0.70

çīĪ

0.67

æĪ¦

0.66

sein

0.65

kish

0.65

INGTON

0.65

zech

0.65

esson

0.64

Activations Density 0.013%

references to related topics or content as indicated by the "See also" labels

the phrase "see also"

No Comments

No Known Activations