INDEX

Explanations

mentions of various types of products

oai_token-act-pair · gpt-3.5-turbo

mentions of various products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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¬

-0.79

CLASSIFIED

-0.72

roe

-0.68

IELD

-0.66

noon

-0.65

ITED

-0.62

ference

-0.62

 Stud

-0.62

ODE

-0.60

otos

-0.60

POSITIVE LOGITS

 products

0.91

 packaging

0.90

ively

0.89

ivity

0.85

 marketed

0.83

uria

0.82

Products

0.81

kit

0.81

umers

0.79

ĸļ

0.78

Activations Density 0.028%

mentions of various types of products

mentions of various products

No Comments

No Known Activations