INDEX

Explanations

terms related to military activities

oai_token-act-pair · gpt-3.5-turbo

terms related to military and conflict situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Panther

-0.69

 Wildcats

-0.65

 Speech

-0.65

 Weinstein

-0.65

 Kell

-0.63

bed

-0.63

Bri

-0.62

 Meal

-0.62

 Blow

-0.61

 miscarriage

-0.61

POSITIVE LOGITS

acies

1.40

acist

1.15

antis

1.12

aton

1.12

ateg

1.10

ales

1.09

acists

1.08

atory

1.08

acy

1.06

ates

1.05

Activations Density 0.056%

terms related to military activities

terms related to military and conflict situations

No Comments

No Known Activations