INDEX

Explanations

proper nouns related to governmental or organizational entities with the word "People" in their name

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "People" in various contexts

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

 flatt

-0.71

quo

-0.68

roll

-0.65

inet

-0.64

 shape

-0.63

 trim

-0.62

cv

-0.61

ric

-0.60

ral

-0.60

 tact

-0.60

POSITIVE LOGITS

 Rights

1.08

 Matters

0.99

 Programs

0.95

 Responsibility

0.94

 Club

0.89

 Clinic

0.88

 Disorder

0.88

itarian

0.86

 Activities

0.86

 Week

0.86

Activations Density 0.079%

proper nouns related to governmental or organizational entities with the word "People" in their name

occurrences of the word "People" in various contexts

No Comments

No Known Activations