INDEX

Explanations

places or structures that have been destroyed or affected in some negative way

oai_token-act-pair · gpt-3.5-turbo

phrases related to destruction and damage in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Austral

-0.70

-0.69

ONEY

-0.67

arget

-0.66

rities

-0.66

 CARD

-0.65

tumblr

-0.64

cest

-0.63

 inconsistency

-0.62

john

-0.61

POSITIVE LOGITS

 rubble

0.98

 habitable

0.92

 deserted

0.88

 limestone

0.86

 farmland

0.84

 inhabited

0.84

 desolate

0.84

 vacated

0.84

 adjoining

0.83

 reopened

0.83

Activations Density 0.338%

places or structures that have been destroyed or affected in some negative way

phrases related to destruction and damage in various contexts

No Comments

No Known Activations