INDEX

Explanations

mentions of political positions or roles

oai_token-act-pair · gpt-3.5-turbo

references to politicians, specifically senators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Britann

-0.76

 upkeep

-0.65

 showc

-0.64

illusion

-0.62

lay

-0.62

RM

-0.62

 Ubisoft

-0.61

usterity

-0.60

 behavi

-0.60

 curfew

-0.60

POSITIVE LOGITS

ial

1.12

 Grassley

1.02

 Dianne

0.98

 Schumer

0.92

 Bernie

0.87

 Leah

0.87

ileaks

0.87

pai

0.87

 McCain

0.86

 Cory

0.84

Activations Density 0.027%

mentions of political positions or roles

references to politicians, specifically senators

No Comments

No Known Activations