INDEX

Explanations

specific numbered entities

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics

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

 bung

-0.74

aunt

-0.71

ãĤ¬

-0.68

ãĤ±

-0.64

 maiden

-0.62

rew

-0.62

 Bung

-0.61

 gimmick

-0.61

 revenge

-0.60

manship

-0.60

POSITIVE LOGITS

Footnote

1.01

Î²

0.89

âĢł

0.84

].

0.82

SOURCE

0.81

],[

0.81

CFR

0.79

MRI

0.79

 Specifically

0.77

 fluoride

0.76

Activations Density 0.192%

specific numbered entities

numerical data or statistics

No Comments

No Known Activations