INDEX

Explanations

reports of violent events resulting in multiple casualties

oai_token-act-pair · gpt-3.5-turbo

phrases related to death and casualties

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

wcsstore

-1.01

atum

-0.75

isphere

-0.73

soType

-0.69

chart

-0.69

ater

-0.68

arity

-0.67

 athlet

-0.67

aters

-0.67

anwhile

-0.67

POSITIVE LOGITS

 civilians

0.99

 spree

0.96

him

0.86

 innocent

0.80

 dozens

0.79

 rampage

0.78

 somebody

0.78

 terrorists

0.78

 Osama

0.75

 lots

0.75

Activations Density 0.060%

reports of violent events resulting in multiple casualties

phrases related to death and casualties

No Comments

No Known Activations