INDEX

Explanations

information about individuals involved in various incidents or actions

oai_token-act-pair · gpt-3.5-turbo

references to individuals in various contexts, particularly in relation to incidents or events

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

 everlasting

-0.78

foundation

-0.71

 emphasizing

-0.71

 Anything

-0.64

 concentrating

-0.64

 focusing

-0.63

 excluding

-0.61

ÂłÂłÂłÂł

-0.61

 refining

-0.61

 everywhere

-0.60

POSITIVE LOGITS

 died

1.08

 allegedly

1.07

 escaped

1.00

 perished

0.99

 survived

0.98

 appeared

0.97

 fled

0.97

 disappeared

0.97

 crashed

0.96

 belonged

0.95

Activations Density 0.135%

information about individuals involved in various incidents or actions

references to individuals in various contexts, particularly in relation to incidents or events

No Comments

No Known Activations