INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names

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

enture

-1.01

cffff

-0.94

raq

-0.80

mental

-0.80

flies

-0.79

lege

-0.79

apple

-0.78

rador

-0.75

nexus

-0.75

pmwiki

-0.74

POSITIVE LOGITS

 Foley

0.95

von

0.94

Von

0.93

 Robertson

0.91

 Nolan

0.86

Yor

0.86

 Kessler

0.85

 Singer

0.85

Agu

0.85

 Slater

0.85

Activations Density 0.024%

names of individuals

mentions of specific names

No Comments

No Known Activations