INDEX

Explanations

names of computer programs or technologies

oai_token-act-pair · gpt-3.5-turbo

references to specific games and gaming terminology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.67

rower

-0.67

 workforce

-0.63

 employee

-0.63

 hump

-0.62

 bicycl

-0.61

dog

-0.60

 hitter

-0.59

 whale

-0.59

 poppy

-0.59

POSITIVE LOGITS

 Madness

0.81

 onwards

0.81

livion

0.78

+.

0.77

Bound

0.73

ĨĴ

0.73

ipedia

0.71

 Gaia

0.70

orld

0.70

 Alley

0.69

Activations Density 0.594%

names of computer programs or technologies

references to specific games and gaming terminology

No Comments

No Known Activations