INDEX

Explanations

phrases related to location or direction

oai_token-act-pair · gpt-3.5-turbo

conjunctions and linkers that connect ideas or clauses

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

ore

-0.69

enance

-0.68

 Doodle

-0.67

argo

-0.65

rite

-0.61

itar

-0.61

 Monteneg

-0.59

eer

-0.59

els

-0.59

 decentral

-0.58

POSITIVE LOGITS

 namely

0.99

whether

0.80

 sqor

0.79

viz

0.79

anwhile

0.75

 sidx

0.73

excluding

0.72

\":

0.71

 partName

0.70

were

0.69

Activations Density 0.785%

phrases related to location or direction

conjunctions and linkers that connect ideas or clauses

No Comments

No Known Activations