INDEX

Explanations

technical terms related to piping and heat management

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'p'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

NESS

-0.78

 Lauder

-0.74

 GOODMAN

-0.71

æ©Ł

-0.70

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.69

å§«

-0.67

 Palest

-0.67

è£

-0.66

 Milky

-0.66

MpServer

-0.65

POSITIVE LOGITS

ossible

1.44

redict

1.32

ulse

1.30

ixels

1.25

resents

1.23

ivot

1.23

ilot

1.21

uppet

1.21

overty

1.20

okemon

1.18

Activations Density 0.037%

technical terms related to piping and heat management

occurrences of the letter 'p'

No Comments

No Known Activations