INDEX

Explanations

dots or words related to dots

oai_token-act-pair · gpt-3.5-turbo

references to "dots" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IENCE

-0.70

ANS

-0.69

CVE

-0.69

 HELP

-0.64

ISTORY

-0.64

idential

-0.62

 Referred

-0.62

 Belief

-0.62

 srfAttach

-0.61

FUL

-0.61

POSITIVE LOGITS

dot

1.28

dot

0.97

olor

0.90

uate

0.84

eret

0.84

biz

0.81

rix

0.80

ching

0.76

ronics

0.74

roll

0.74

Activations Density 0.008%

dots or words related to dots

references to "dots" in various contexts

No Comments

No Known Activations