INDEX

Explanations

references to transportation infrastructure, particularly focusing on roads and their conditions

oai_token-act-pair · gpt-3.5-turbo

references to roads and their conditions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ividual

-0.88

ority

-0.81

arians

-0.75

illian

-0.72

 Wong

-0.70

iaries

-0.69

 homegrown

-0.69

rators

-0.67

arian

-0.66

tle

-0.65

POSITIVE LOGITS

ways

1.17

 roads

1.05

blocks

0.98

 highways

0.93

 Roads

0.90

block

0.90

lane

0.89

 tyres

0.89

road

0.88

 arteries

0.87

Activations Density 0.023%

references to transportation infrastructure, particularly focusing on roads and their conditions

references to roads and their conditions

No Comments

No Known Activations