INDEX

Explanations

sentences indicating lack of clarity or uncertainty

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or ambiguity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

INT

-0.83

zig

-0.72

ocard

-0.71

jet

-0.71

inse

-0.67

@#&

-0.66

vis

-0.66

clerosis

-0.65

tha

-0.65

tin

-0.65

POSITIVE LOGITS

 whether

0.86

how

0.74

 jurisdiction

0.74

ether

0.73

 quantity

0.71

abouts

0.67

ly

0.66

why

0.65

eth

0.64

ively

0.63

Activations Density 0.032%

sentences indicating lack of clarity or uncertainty

phrases indicating uncertainty or ambiguity

No Comments

No Known Activations