INDEX

Explanations

terms related to war and conflict

oai_token-act-pair · gpt-3.5-turbo

references to countries in conflict and the associated humanitarian crises

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

 basis

-0.80

OPLE

-0.72

 breakfast

-0.68

 decimal

-0.68

 pencil

-0.67

 Gifts

-0.65

 decency

-0.65

 finishes

-0.65

 directives

-0.65

 arts

-0.65

POSITIVE LOGITS

prone

1.71

ridden

1.62

torn

1.54

inducing

1.49

resistant

1.42

laden

1.41

affected

1.36

induced

1.34

rav

1.33

filled

1.26

Activations Density 0.063%

terms related to war and conflict

references to countries in conflict and the associated humanitarian crises

No Comments

No Known Activations