INDEX

Explanations

references to specific locations or cities

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and specific formatting elements in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thood

-0.65

natureconservancy

-0.64

dn

-0.63

itary

-0.61

tons

-0.61

 cabinets

-0.61

 machines

-0.60

units

-0.60

scope

-0.59

products

-0.59

POSITIVE LOGITS

 CITY

1.01

INC

0.93

MEN

0.87

ANE

0.87

 GOODMAN

0.86

INC

0.85

IDER

0.85

ANK

0.83

 VIDE

0.83

MEN

0.82

Activations Density 0.059%

references to specific locations or cities

punctuation marks and specific formatting elements in the text

No Comments

No Known Activations