INDEX

Explanations

proper nouns or entities starting with 'Us'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Us" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

TAM

-0.61

 poaching

-0.58

BJ

-0.57

CPC

-0.57

 laureate

-0.57

 plaque

-0.56

 Pandora

-0.55

hetti

-0.55

 confinement

-0.54

 flare

-0.54

POSITIVE LOGITS

hers

1.30

ual

1.20

agi

1.20

ages

1.18

ername

1.10

urers

1.04

her

1.01

ern

1.01

leep

1.01

ury

1.00

Activations Density 0.027%

proper nouns or entities starting with 'Us'

occurrences of the word "Us" and its variations

No Comments

No Known Activations