INDEX

Explanations

numeric values with varying patterns

oai_token-act-pair · gpt-3.5-turbo

technical or coded information, often related to data processing or programming

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ISA

-0.55

GHz

-0.48

 landmark

-0.48

ensional

-0.47

 predictor

-0.47

 pinnacle

-0.46

Tud

-0.46

ishops

-0.46

 impeachment

-0.45

 veto

-0.45

POSITIVE LOGITS

 tears

0.56

anca

0.54

exempt

0.54

phia

0.53

oult

0.53

sic

0.52

utils

0.52

 Converted

0.52

unct

0.51

«

0.49

Activations Density 0.740%

numeric values with varying patterns

technical or coded information, often related to data processing or programming

No Comments

No Known Activations