INDEX

Explanations

acronyms and abbreviations used in academic or professional contexts

oai_token-act-pair · gpt-3.5-turbo

acronyms or abbreviations related to organizations or programs

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

enegger

-0.82

Magikarp

-0.80

\":

-0.77

sburgh

-0.74

)=(

-0.74

doms

-0.74

ãĤ¦ãĤ¹

-0.72

uyomi

-0.70

acters

-0.68

ãĤª

-0.68

POSITIVE LOGITS

FI

1.17

BC

1.14

IS

1.14

TF

1.12

IST

1.09

FP

1.09

OP

1.05

AC

1.05

SA

1.04

DT

1.04

Activations Density 0.184%

acronyms and abbreviations used in academic or professional contexts

acronyms or abbreviations related to organizations or programs

No Comments

No Known Activations