INDEX

Explanations

phrases indicating inclusion or mention of multiple entities or facts

oai_token-act-pair · gpt-3.5-turbo

phrases indicative of membership or association in a group or category

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

([

-0.74

 Period

-0.74

bane

-0.74

ynthesis

-0.70

hiro

-0.68

ensis

-0.67

cycle

-0.65

arden

-0.65

mop

-0.65

ategory

-0.65

POSITIVE LOGITS

 casualties

1.03

 targets

1.02

 beneficiaries

1.01

 findings

0.99

 recipients

0.98

 surprises

0.95

 topics

0.94

 dozen

0.89

 plaintiffs

0.89

 revelations

0.89

Activations Density 0.182%

phrases indicating inclusion or mention of multiple entities or facts

phrases indicative of membership or association in a group or category

No Comments

No Known Activations