INDEX

Explanations

objects and actions related to physical altercations or disturbances

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "and" 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

imester

-0.88

irin

-0.78

idem

-0.73

":"/

-0.73

imilation

-0.72

ummer

-0.72

>[

-0.71

arak

-0.71

profit

-0.70

iller

-0.69

POSITIVE LOGITS

 other

1.11

 assorted

1.06

 others

0.90

 urged

0.83

 chanted

0.83

 another

0.81

 proceeded

0.80

 drank

0.79

 sprayed

0.79

 asked

0.78

Activations Density 0.306%

objects and actions related to physical altercations or disturbances

occurrences of the word "and" in various contexts

No Comments

No Known Activations