INDEX

Explanations

specific locations or addresses on roads

oai_token-act-pair · gpt-3.5-turbo

references to specific road names

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

arians

-0.76

illian

-0.72

ERAL

-0.71

irements

-0.70

glers

-0.70

arian

-0.69

uated

-0.69

 Lauder

-0.69

 Wong

-0.69

pes

-0.68

POSITIVE LOGITS

side

0.93

road

0.92

 Racer

0.92

trip

0.92

 Roads

0.90

stead

0.88

runner

0.86

 Road

0.84

ways

0.82

course

0.81

Activations Density 0.011%

specific locations or addresses on roads

references to specific road names

No Comments

No Known Activations