INDEX

Explanations

phrases related to academic publications, specifically in the context of the National Academy of Sciences

oai_token-act-pair · gpt-3.5-turbo

references to academic institutions and scientific papers

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

matter

-0.78

ahan

-0.73

forth

-0.72

alore

-0.72

cloud

-0.72

baugh

-0.71

gaard

-0.70

hus

-0.70

downs

-0.69

 quar

-0.67

POSITIVE LOGITS

 Sciences

1.04

 Pediatrics

0.86

 Nations

0.84

 Computing

0.83

 Appeal

0.78

 Arts

0.75

 Science

0.75

 Letters

0.74

 Instruction

0.73

 Voters

0.73

Activations Density 0.070%

phrases related to academic publications, specifically in the context of the National Academy of Sciences

references to academic institutions and scientific papers

No Comments

No Known Activations