INDEX

Explanations

mentions of inspectors or inspector generals

oai_token-act-pair · gpt-3.5-turbo

references to inspectors or inspector roles 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

theless

-1.07

birth

-0.78

maps

-0.69

eton

-0.69

eda

-0.69

erry

-0.68

words

-0.67

asted

-0.66

demand

-0.66

esville

-0.65

POSITIVE LOGITS

 Gadget

1.15

 Spac

0.87

Reviewer

0.82

atis

0.81

 Inspector

0.79

atus

0.73

 inspector

0.73

General

0.72

 General

0.72

 Institution

0.71

Activations Density 0.013%

mentions of inspectors or inspector generals

references to inspectors or inspector roles in various contexts

No Comments

No Known Activations