INDEX

Explanations

mentions of specific names

oai_token-act-pair · gpt-3.5-turbo

names of individuals and entities

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

veland

-0.77

Phot

-0.68

 STATS

-0.67

rawdownloadcloneembedreportprint

-0.66

âķĲ

-0.65

 Trance

-0.65

Initialized

-0.65

âķĲâķĲ

-0.64

ĺħ

-0.64

 DRAG

-0.63

POSITIVE LOGITS

glers

0.92

lar

0.91

lass

0.87

rum

0.86

akia

0.85

rophic

0.84

aeus

0.83

elin

0.83

lasses

0.83

ational

0.83

Activations Density 0.042%

mentions of specific names

names of individuals and entities

No Comments

No Known Activations