INDEX

Explanations

terms related to obstacles or hindrances

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to obstruction or hindrance

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ocene

-0.75

 Waterloo

-0.73

ITV

-0.72

 Catalyst

-0.70

 Comet

-0.69

Elect

-0.67

isable

-0.66

iser

-0.64

 VIDEOS

-0.63

 Uniform

-0.63

POSITIVE LOGITS

 hind

1.26

rance

0.96

 hinder

0.92

pling

0.85

sight

0.80

bone

0.79

quarters

0.79

¿½

0.79

wart

0.76

oon

0.76

Activations Density 0.007%

terms related to obstacles or hindrances

words and phrases related to obstruction or hindrance

No Comments

No Known Activations