INDEX

Explanations

words related to the usage or implementation of something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "usage."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Barg

-0.71

tell

-0.65

mun

-0.65

ducers

-0.63

inosaur

-0.62

rop

-0.62

hair

-0.61

ridge

-0.61

 Mercy

-0.59

present

-0.59

POSITIVE LOGITS

 usage

0.86

 habits

0.85

ername

0.79

 misuse

0.78

 patterns

0.77

 diffusion

0.75

iences

0.73

 guiActiveUn

0.72

itures

0.71

 utilization

0.70

Activations Density 0.014%

words related to the usage or implementation of something

occurrences of the word "usage."

No Comments

No Known Activations