INDEX

Explanations

numerical ordinals (e.g., 1st, 2nd, 3rd, etc.)

oai_token-act-pair · gpt-3.5-turbo

ordinal indicators or rankings

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

zsche

-0.64

itri

-0.63

Statistics

-0.62

 Kafka

-0.62

uploads

-0.61

 Gould

-0.60

acci

-0.60

 Canaver

-0.59

ITED

-0.59

edi

-0.57

POSITIVE LOGITS

ousand

0.98

 Anniversary

0.98

ulhu

0.92

 Amendment

0.91

 anniversary

0.90

 percentile

0.87

oppers

0.85

ursday

0.85

ieves

0.83

irty

0.82

Activations Density 0.037%

numerical ordinals (e.g., 1st, 2nd, 3rd, etc.)

ordinal indicators or rankings

No Comments

No Known Activations