INDEX

Explanations

mentions of spitting or instances of physical conflict

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "spat" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ACTED

-0.69

PORT

-0.65

ports

-0.64

ITNESS

-0.62

yrics

-0.61

uliffe

-0.61

annis

-0.60

versions

-0.60

export

-0.60

ãģķ

-0.60

POSITIVE LOGITS

 spat

1.13

ially

1.03

ually

0.89

ters

0.85

hes

0.82

escription

0.73

iot

0.72

uality

0.72

 challeng

0.71

 Brus

0.70

Activations Density 0.008%

mentions of spitting or instances of physical conflict

occurrences of the word "spat" and related variations

No Comments

No Known Activations