INDEX

Explanations

prepositions followed by a distance or measurement

oai_token-act-pair · gpt-3.5-turbo

phrases indicating proximity or closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ãĥ£

-0.75

cow

-0.66

 goodbye

-0.62

ple

-0.62

ãĥ¼ãĤ¯

-0.61

cu

-0.61

ANS

-0.61

de

-0.60

Definition

-0.60

rod

-0.60

POSITIVE LOGITS

ieth

0.87

 bounds

0.86

isine

0.83

imore

0.81

ĵĺ

0.80

isode

0.79

 parentheses

0.76

emort

0.76

ciating

0.72

 orbit

0.72

Activations Density 0.025%

prepositions followed by a distance or measurement

phrases indicating proximity or closeness

No Comments

No Known Activations