INDEX

Explanations

words related to events or actions that involve recommendations, celebrations, or emotional responses

oai_token-act-pair · gpt-3.5-turbo

words related to revealing information or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 intrusion

-0.65

 Dragonbound

-0.64

owe

-0.57

 FISA

-0.57

 impossibility

-0.56

icipated

-0.56

Doe

-0.55

ISO

-0.55

iane

-0.55

 Observer

-0.55

POSITIVE LOGITS

llers

1.58

ller

1.55

lling

1.53

ptions

1.29

ptic

1.27

brate

1.27

lled

1.27

ven

1.27

vered

1.26

brates

1.23

Activations Density 0.160%

words related to events or actions that involve recommendations, celebrations, or emotional responses

words related to revealing information or events

No Comments

No Known Activations