INDEX

Explanations

references to criminal incidents involving men

oai_token-act-pair · gpt-3.5-turbo

references to male individuals, particularly mentioning their age

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

çļ

-0.74

 Grid

-0.69

ãĤ¦

-0.68

 Machines

-0.68

 chars

-0.67

ffee

-0.65

 Journals

-0.64

 instr

-0.64

ellect

-0.63

aeda

-0.62

POSITIVE LOGITS

hunt

1.00

endez

0.88

who

0.83

nered

0.76

 accused

0.74

 gunman

0.74

WHO

0.74

 SWAT

0.72

ishly

0.71

ish

0.70

Activations Density 0.128%

references to criminal incidents involving men

references to male individuals, particularly mentioning their age

No Comments

No Known Activations