INDEX

Explanations

mentions of government positions or officials, particularly those related to defense and health

oai_token-act-pair · gpt-3.5-turbo

references to government officials and their titles

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

::::::::

-0.73

ucha

-0.72

 Artists

-0.68

Tree

-0.65

forming

-0.65

VALUE

-0.65

liga

-0.62

 Artist

-0.62

Film

-0.62

#$#$

-0.62

POSITIVE LOGITS

 Shaun

0.83

 Ernest

0.82

 Marino

0.81

vette

0.80

 Salman

0.78

 Suzanne

0.78

 Steven

0.77

Liz

0.77

 Michele

0.77

 Khalid

0.77

Activations Density 0.079%

mentions of government positions or officials, particularly those related to defense and health

references to government officials and their titles

No Comments

No Known Activations