INDEX

Explanations

words related to criminal activities and law enforcement

oai_token-act-pair · gpt-3.5-turbo

conjunctions indicating multiple associated events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ADVERTISEMENT

-0.74

DX

-0.71

Xbox

-0.71

NULL

-0.69

izen

-0.68

omi

-0.68

Deal

-0.67

Morning

-0.67

 Powered

-0.66

meric

-0.66

POSITIVE LOGITS

 consequently

1.15

 therefore

1.13

 thus

1.10

 then

1.04

 thereby

1.00

 hence

0.99

 subsequently

0.96

 thence

0.93

 possibly

0.93

 secondly

0.90

Activations Density 0.697%

words related to criminal activities and law enforcement

conjunctions indicating multiple associated events or actions

No Comments

No Known Activations