INDEX

Explanations

keywords related to trains and train stations

oai_token-act-pair · gpt-3.5-turbo

references to trains and related rail transportation

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

erenn

-0.85

laus

-0.75

osi

-0.73

eff

-0.68

theless

-0.67

Ĥİ

-0.66

 moot

-0.62

monds

-0.61

axter

-0.61

ogene

-0.61

POSITIVE LOGITS

wreck

1.09

 conductor

0.99

roads

0.94

 trains

0.91

loads

0.89

girls

0.84

ings

0.82

 Tracks

0.82

 tracks

0.81

ees

0.81

Activations Density 0.018%

keywords related to trains and train stations

references to trains and related rail transportation

No Comments

No Known Activations