INDEX

Explanations

dates written in the format "day month year"

oai_token-act-pair · gpt-3.5-turbo

numerical values or references related to statistics or data points

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

enhagen

-0.95

orc

-0.91

ensed

-0.79

mble

-0.78

aired

-0.76

 regenerate

-0.75

ovie

-0.75

odynamic

-0.74

onite

-0.73

odynam

-0.71

POSITIVE LOGITS

rd

0.88

0.87

0.85

0.82

0.79

0.78

0.77

Activations Density 0.031%

dates written in the format "day month year"

numerical values or references related to statistics or data points

No Comments

No Known Activations