INDEX

Explanations

mentions of specific policies or efforts being pursued or implemented

oai_token-act-pair · gpt-3.5-turbo

references to governmental policies

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

ITNESS

-0.83

parts

-0.75

lihood

-0.72

 Flavoring

-0.71

issan

-0.71

 Stain

-0.69

athan

-0.69

Sud

-0.69

 Barker

-0.67

CLASSIFIED

-0.65

POSITIVE LOGITS

 enacted

0.96

 governing

0.95

 policies

0.94

 implemented

0.83

 prescriptions

0.82

 restricting

0.82

 affecting

0.81

olicy

0.80

 imposed

0.80

 policy

0.79

Activations Density 0.022%

mentions of specific policies or efforts being pursued or implemented

references to governmental policies

No Comments

No Known Activations