INDEX

Explanations

technical terms related to requirements or qualifications

oai_token-act-pair · gpt-3.5-turbo

phrases indicating necessity or obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ight

-0.76

vironment

-0.74

 Mouth

-0.68

ocent

-0.67

 Dong

-0.67

 Tate

-0.66

uay

-0.65

str

-0.65

ning

-0.65

Ter

-0.64

POSITIVE LOGITS

 confir

0.92

 guiActiveUn

0.91

 disclosures

0.80

 aback

0.80

 prerequisite

0.78

cffff

0.78

MENTS

0.76

 complying

0.74

 eleph

0.74

 requirement

0.73

Activations Density 0.015%

technical terms related to requirements or qualifications

phrases indicating necessity or obligations

No Comments

No Known Activations