INDEX

Explanations

the name "Eve" at various intensities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Eve" in various contexts

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

aceutical

-0.89

enegger

-0.77

Americans

-0.74

oros

-0.69

omo

-0.68

iferation

-0.67

alcohol

-0.67

oho

-0.67

ariat

-0.67

pmwiki

-0.67

POSITIVE LOGITS

rette

1.23

lyn

1.22

Eve

1.09

lla

0.97

lynn

0.91

 Valkyrie

0.88

lling

0.83

ilon

0.83

eve

0.80

llers

0.79

Activations Density 0.019%

the name "Eve" at various intensities

occurrences of the word "Eve" in various contexts

No Comments

No Known Activations