INDEX

Explanations

names of specific locations or entities

oai_token-act-pair · gpt-3.5-turbo

specific names and terms related to locations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 pand

-0.84

ptions

-0.83

cised

-0.77

sembly

-0.73

 microscope

-0.65

 YEAR

-0.64

 Monkey

-0.62

ption

-0.62

wrapper

-0.62

 Panda

-0.61

POSITIVE LOGITS

gow

0.96

orough

0.92

Ô

0.88

iana

0.82

nih

0.79

Osh

0.78

 Lynd

0.75

sburgh

0.74

ijn

0.73

 Pike

0.72

Activations Density 0.017%

names of specific locations or entities

specific names and terms related to locations and organizations

No Comments

No Known Activations