INDEX

Explanations

scientific or technical terms related to products or technologies

oai_token-act-pair · gpt-3.5-turbo

subordinate clauses that introduce defining characteristics or explanations

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

 Doctrine

-0.72

hips

-0.69

 wounding

-0.60

 Corps

-0.59

 Standing

-0.59

 Anthrop

-0.59

Neill

-0.58

hat

-0.57

WARE

-0.57

Guest

-0.57

POSITIVE LOGITS

 accompanies

1.03

 generates

0.89

 arose

0.89

 produces

0.88

 enhances

0.88

 extends

0.87

 creates

0.86

allows

0.86

 satisfies

0.86

 enables

0.85

Activations Density 0.245%

scientific or technical terms related to products or technologies

subordinate clauses that introduce defining characteristics or explanations

No Comments

No Known Activations