INDEX

Explanations

words related to associations or connections between different entities

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate connections or relationships between different subjects or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 actionGroup

-0.65

 Submission

-0.59

 VIDEOS

-0.59

schild

-0.56

iott

-0.56

oker

-0.55

 Subtle

-0.55

Ħ¢

-0.53

 impression

-0.53

cknow

-0.52

POSITIVE LOGITS

 thereto

1.02

 closely

0.86

to

0.84

 intimately

0.82

 geographically

0.81

ged

0.81

 directly

0.80

 together

0.77

 statically

0.76

linked

0.74

Activations Density 0.074%

words related to associations or connections between different entities

phrases that indicate connections or relationships between different subjects or entities

No Comments

No Known Activations