INDEX

Explanations

occurrences of violent events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "during" in relation to events or actions

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

Negative Logits

ovan

-0.81

âĺ

-0.73

oros

-0.72

notation

-0.68

pots

-0.66

ants

-0.66

Companies

-0.65

Stars

-0.65

anium

-0.64

inkle

-0.64

POSITIVE LOGITS

 clashes

1.19

 celebrations

1.07

 demonstrations

1.03

 festivities

1.02

 renovations

1.00

 riots

0.99

 protests

0.98

 daylight

0.95

 disturbances

0.92

 Ramadan

0.90

Activations Density 0.129%

occurrences of violent events

occurrences of the word "during" in relation to events or actions

No Known Activations