INDEX

Explanations

information related to various products

oai_token-act-pair · gpt-3.5-turbo

references to various products

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

âĸ¬

-0.73

CLASSIFIED

-0.71

roe

-0.70

IELD

-0.68

noon

-0.65

 Nights

-0.63

ODE

-0.63

 Tale

-0.63

 lone

-0.62

ITED

-0.61

POSITIVE LOGITS

ively

0.97

 packaging

0.97

 marketed

0.92

ivity

0.92

 products

0.90

kit

0.82

Products

0.81

umers

0.79

isine

0.75

afety

0.75

Activations Density 0.027%

information related to various products

references to various products

No Comments

No Known Activations