INDEX

Explanations

phrases related to capping or limiting something

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of "california" or "CA"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

idad

-0.66

 Fields

-0.66

CRE

-0.61

thia

-0.59

itarian

-0.58

 Dynamics

-0.57

alia

-0.57

 Dreams

-0.56

ainment

-0.56

OURCE

-0.55

POSITIVE LOGITS

ffer

0.91

reci

0.89

fter

0.89

pperc

0.86

utions

0.86

pping

0.85

asus

0.83

pered

0.78

udic

0.77

fters

0.77

Activations Density 0.048%

phrases related to capping or limiting something

phrases related to the concept of "california" or "CA"

No Comments

No Known Activations