INDEX

Explanations

phrases that express contradiction or opposition

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate skepticism or contradiction

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

entin

-0.76

aturated

-0.65

pez

-0.60

prus

-0.60

uzz

-0.59

active

-0.58

ournals

-0.58

esta

-0.58

issance

-0.57

waukee

-0.57

POSITIVE LOGITS

 standpoint

1.05

 perspective

0.89

 contrary

0.88

 point

0.78

 anyway

0.77

 least

0.77

 viewpoint

0.75

 extent

0.74

 approximation

0.71

 anyways

0.70

Activations Density 0.836%

phrases that express contradiction or opposition

phrases that indicate skepticism or contradiction

No Comments

No Known Activations