INDEX

Explanations

references to law enforcement accountability

oai_token-act-pair · gpt-3.5-turbo

repetitive mentions of a specific term, likely related to a subject or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 juggling

-0.76

wright

-0.75

 Oblivion

-0.63

 directions

-0.63

AE

-0.62

heads

-0.61

 Metatron

-0.61

 Gutenberg

-0.60

 Fiber

-0.59

tons

-0.59

POSITIVE LOGITS

pper

1.26

arez

1.21

icidal

1.20

icides

1.17

icide

1.10

pped

1.08

itable

1.06

iler

1.06

zanne

1.05

iling

1.03

Activations Density 0.016%

references to law enforcement accountability

repetitive mentions of a specific term, likely related to a subject or entity

No Comments

No Known Activations