INDEX

Explanations

words related to angles and geometry

oai_token-act-pair · gpt-3.5-turbo

references to angles in various contexts

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

raltar

-0.88

icious

-0.79

ingham

-0.78

ledged

-0.77

å£«

-0.77

TY

-0.76

ifying

-0.76

ULE

-0.75

weet

-0.75

ains

-0.75

POSITIVE LOGITS

 angle

1.18

 angles

1.09

 brackets

1.07

 jerk

0.84

 Angle

0.80

 lens

0.75

 bends

0.75

 thereto

0.74

 elevation

0.73

hog

0.71

Activations Density 0.018%

words related to angles and geometry

references to angles in various contexts

No Comments

No Known Activations