INDEX

Explanations

references to micro-related topics or entities

oai_token-act-pair · gpt-3.5-turbo

terms related to micro technology or micro systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

UAL

-0.79

aukee

-0.73

igham

-0.69

 shortest

-0.65

lain

-0.65

 Cursed

-0.65

IUM

-0.64

Eve

-0.64

 Guilty

-0.64

"},"

-0.63

POSITIVE LOGITS

seconds

1.30

organisms

1.26

cos

1.21

gravity

1.20

processor

1.16

chip

1.13

bial

1.09

controller

1.08

cephal

1.08

second

1.07

Activations Density 0.017%

references to micro-related topics or entities

terms related to micro technology or micro systems

No Comments

No Known Activations