INDEX

Explanations

proper nouns related to bridges

oai_token-act-pair · gpt-3.5-turbo

mentions of bridges

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

arily

-0.82

psy

-0.72

resy

-0.69

phis

-0.69

ccording

-0.68

egal

-0.67

matically

-0.66

iencies

-0.65

nutrition

-0.65

mons

-0.65

POSITIVE LOGITS

port

1.04

 Bridges

0.93

 Bridge

0.92

 Strait

0.90

ports

0.87

bridge

0.85

yard

0.82

 Simulator

0.82

 bridges

0.81

roads

0.80

Activations Density 0.014%

proper nouns related to bridges

mentions of bridges

No Comments

No Known Activations