INDEX

Explanations

phrases related to investigating or examining a topic further

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the action of examining or considering something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hop

-0.68

gob

-0.67

bender

-0.66

sworth

-0.65

ienne

-0.64

stick

-0.64

patrick

-0.62

 bang

-0.61

loaded

-0.61

lisher

-0.58

POSITIVE LOGITS

 UFOs

0.74

dfx

0.70

 feasibility

0.70

 specifics

0.68

 whether

0.66

clusion

0.63

itutional

0.63

ienced

0.61

 allegations

0.60

onduct

0.60

Activations Density 0.033%

phrases related to investigating or examining a topic further

phrases indicating the action of examining or considering something

No Comments

No Known Activations