INDEX

Explanations

words related to computer programming or coding, specifically those with underscores or special characters

oai_token-act-pair · gpt-3.5-turbo

numerical values and related sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ĸļ

-0.79

 Haku

-0.77

Syd

-0.76

Sob

-0.74

 Clara

-0.72

Sik

-0.71

 Benny

-0.71

 Robot

-0.70

Yad

-0.69

Rik

-0.69

POSITIVE LOGITS

ó

1.09

********************************

1.01

Reply

1.01

Ident

0.99

Impl

0.98

RFC

0.96

RAW

0.96

together

0.96

DES

0.95

--------------------------------

0.95

Activations Density 0.109%

words related to computer programming or coding, specifically those with underscores or special characters

numerical values and related sequences

No Comments

No Known Activations