INDEX

Explanations

names or titles related to people in the film industry, such as directors or writers

oai_token-act-pair · gpt-3.5-turbo

mentions of directors in a film context

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

MpServer

-0.81

 Leafs

-0.71

 Labrador

-0.66

cup

-0.65

affle

-0.64

bitcoin

-0.64

ulia

-0.64

abies

-0.62

latable

-0.62

 Exercise

-0.61

POSITIVE LOGITS

urally

0.96

 studios

0.93

 Studios

0.88

ial

0.86

ography

0.85

 filmmaker

0.85

 films

0.83

 filmmakers

0.82

director

0.82

cember

0.81

Activations Density 0.042%

names or titles related to people in the film industry, such as directors or writers

mentions of directors in a film context

No Comments

No Known Activations