INDEX

Explanations

phrases related to violent actions or crimes

oai_token-act-pair · gpt-3.5-turbo

references to violent crimes and suspects involved in them

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

Enhanced

-0.66

 ausp

-0.65

 introductory

-0.64

podcast

-0.64

oult

-0.62

OLOG

-0.62

 renaissance

-0.62

 advisory

-0.61

 quir

-0.60

IDE

-0.60

POSITIVE LOGITS

angering

0.80

 injuring

0.80

utterstock

0.78

 senseless

0.78

ribly

0.75

 fleeing

0.71

 injure

0.71

 whom

0.70

uckles

0.70

 resisting

0.69

Activations Density 0.953%

phrases related to violent actions or crimes

references to violent crimes and suspects involved in them

No Comments

No Known Activations