INDEX

Explanations

personal names, possibly associated with a position or title

oai_token-act-pair · gpt-3.5-turbo

mentions of people and their roles or contributions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 deport

-0.77

 punishments

-0.72

 deportation

-0.71

 detainees

-0.71

politics

-0.70

 symbolic

-0.70

 executions

-0.70

 judgments

-0.70

 retaliation

-0.69

 killings

-0.68

POSITIVE LOGITS

 Shap

0.87

PhD

0.82

QC

0.79

Found

0.76

 Minion

0.75

 Architects

0.73

 Argon

0.71

âķĲ

0.70

 booth

0.70

LL

0.70

Activations Density 0.797%

personal names, possibly associated with a position or title

mentions of people and their roles or contributions

No Comments

No Known Activations