INDEX

Explanations

proper nouns related to a specific name

oai_token-act-pair · gpt-3.5-turbo

references to polling or surveys

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

stay

-0.72

 Viking

-0.68

CONCLUS

-0.66

ãĤ¨ãĥ«

-0.64

Cay

-0.64

pires

-0.63

 Commando

-0.62

WAYS

-0.62

 rendition

-0.62

ACTED

-0.61

POSITIVE LOGITS

 Poll

1.16

Poll

1.06

poll

1.00

inator

1.00

inators

0.97

ards

0.90

ilon

0.89

ard

0.89

 poll

0.88

arding

0.84

Activations Density 0.005%

proper nouns related to a specific name

references to polling or surveys

No Comments

No Known Activations