INDEX

Explanations

references to police, policing, or policies

oai_token-act-pair · gpt-3.5-turbo

words related to police or policing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

INESS

-0.64

rers

-0.64

ELD

-0.63

uring

-0.62

 Druid

-0.61

------------

-0.59

 receptor

-0.59

 Apprentice

-0.59

 Revel

-0.58

========

-0.57

POSITIVE LOGITS

itely

1.28

arity

1.12

anski

1.06

ishing

1.03

tical

1.02

isher

1.02

ished

1.01

ikarp

0.99

ishes

0.99

ishers

0.98

Activations Density 0.026%

references to police, policing, or policies

words related to police or policing

No Comments

No Known Activations