INDEX

Explanations

phrases related to cessation or stopping of actions

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "cease" and its variations 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 @ 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

 Inquisitor

-0.80

uries

-0.78

ramid

-0.78

swick

-0.76

assium

-0.74

raviolet

-0.72

OTE

-0.72

rium

-0.71

 Aval

-0.70

ammy

-0.69

POSITIVE LOGITS

 cease

0.97

ĸļ

0.86

rences

0.85

 seiz

0.82

 ceases

0.82

²¾

0.76

fires

0.75

 prematurely

0.74

 cessation

0.74

 promptly

0.73

Activations Density 0.008%

phrases related to cessation or stopping of actions

mentions of the word "cease" and its variations in various contexts

No Comments

No Known Activations