INDEX

Explanations

words related to uncertainty or doubt

oai_token-act-pair · gpt-3.5-turbo

phrases expressing uncertainty or lack of knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 nevertheless

-0.86

 nonetheless

-0.79

 indeed

-0.73

ifully

-0.70

moil

-0.69

 curiously

-0.68

 undoubtedly

-0.67

 alternatively

-0.67

vic

-0.66

 strangely

-0.64

POSITIVE LOGITS

 mattered

0.89

 cared

0.82

 bothered

0.73

hin

0.73

 grasp

0.71

know

0.71

FTWARE

0.70

 understood

0.69

 cares

0.68

 bother

0.68

Activations Density 0.065%

words related to uncertainty or doubt

phrases expressing uncertainty or lack of knowledge

No Comments

No Known Activations