INDEX

Explanations

locations where violent incidents have occurred

oai_token-act-pair · gpt-3.5-turbo

specific details related to violent incidents or crime occurrences

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

 transcripts

-0.71

TPP

-0.71

STD

-0.68

 cures

-0.68

 mastered

-0.67

alog

-0.67

 sails

-0.66

rub

-0.65

 assures

-0.64

bill

-0.64

POSITIVE LOGITS

 intersection

0.97

 southwestern

0.94

 Borough

0.93

 Northeast

0.87

 southwest

0.87

 Notting

0.84

 downtown

0.83

 campus

0.83

 southeastern

0.83

 outskirts

0.82

Activations Density 0.346%

locations where violent incidents have occurred

specific details related to violent incidents or crime occurrences

No Comments

No Known Activations