INDEX

Explanations

words relating to spatial adjacency or proximity

oai_token-act-pair · gpt-3.5-turbo

terms related to spatial relationships and adjacency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

fare

-0.81

GO

-0.78

uay

-0.71

tu

-0.70

boys

-0.68

odor

-0.67

zie

-0.65

ball

-0.65

rimp

-0.64

ocker

-0.63

POSITIVE LOGITS

 thereto

0.87

 adjacent

0.75

 adjoining

0.70

minster

0.69

itor

0.69

ãĥ¼ãĥĨ

0.69

ï¸

0.68

 spaces

0.68

66666666

0.68

isode

0.66

Activations Density 0.011%

words relating to spatial adjacency or proximity

terms related to spatial relationships and adjacency

No Comments

No Known Activations