INDEX

Explanations

phrases indicating responsibility or blame

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a specific role or responsibility of parties involved in various actions or situations

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

icone

-0.71

lessly

-0.68

VERT

-0.66

sterdam

-0.66

upon

-0.64

clone

-0.63

beard

-0.63

perse

-0.62

lords

-0.61

ventus

-0.60

POSITIVE LOGITS

 basis

1.42

 behalf

1.42

 grounds

1.35

 doorstep

1.16

eve

1.11

 merits

1.10

 sidelines

1.08

 horizon

1.05

 heels

1.03

 verge

1.03

Activations Density 0.174%

phrases indicating responsibility or blame

phrases that indicate a specific role or responsibility of parties involved in various actions or situations

No Comments

No Known Activations