INDEX

Explanations

names that contain the sequence "ame."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "ame" 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

iversal

-0.80

keyes

-0.79

acea

-0.76

angers

-0.74

rolet

-0.74

oidal

-0.71

aido

-0.69

itely

-0.69

arser

-0.68

dimension

-0.68

POSITIVE LOGITS

leon

1.00

eh

0.91

Ã±a

0.83

0.74

ame

0.74

ez

0.73

eus

0.72

llan

0.72

 Shame

0.71

lihood

0.70

Activations Density 0.016%

names that contain the sequence "ame."

occurrences of the word "ame" in various contexts

No Comments

No Known Activations