INDEX

Explanations

the name "Ero" at varying intensities

oai_token-act-pair · gpt-3.5-turbo

the word "ero" across various contexts and usages

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ividual

-1.07

abase

-0.81

ership

-0.75

 glim

-0.74

ually

-0.74

eenth

-0.73

igators

-0.73

hips

-0.72

amental

-0.72

tin

-0.72

POSITIVE LOGITS

cephal

0.88

zzi

0.82

vous

0.80

ppo

0.80

edia

0.77

bably

0.76

quin

0.75

aster

0.73

eli

0.72

zza

0.71

Activations Density 0.018%

the name "Ero" at varying intensities

the word "ero" across various contexts and usages

No Comments

No Known Activations