INDEX

Explanations

phrases indicating that a statement does not necessarily reflect a specific outcome or meaning

oai_token-act-pair · gpt-3.5-turbo

phrases that convey uncertainty or the concept of non-necessity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

toggle

-0.76

iry

-0.74

eday

-0.73

timer

-0.73

ufact

-0.72

ults

-0.71

maybe

-0.67

 Feld

-0.66

ĸļ

-0.66

fw

-0.65

POSITIVE LOGITS

 equate

0.84

 correlate

0.83

 imply

0.80

 entail

0.76

 synonymous

0.75

 indicative

0.75

 necessarily

0.74

 translate

0.73

 entails

0.71

 agree

0.71

Activations Density 0.038%

phrases indicating that a statement does not necessarily reflect a specific outcome or meaning

phrases that convey uncertainty or the concept of non-necessity

No Comments

No Known Activations