INDEX

Explanations

phrases or terms related to a particular individual or proper name, possibly "Pepper" or a similar name with variations

oai_token-act-pair · gpt-3.5-turbo

words related to or stemming from the term "opper."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ADRA

-0.94

è¯

-0.81

ourced

-0.72

orem

-0.71

ITNESS

-0.71

urers

-0.71

é¾

-0.69

aji

-0.67

clud

-0.66

äºĶ

-0.66

POSITIVE LOGITS

mint

1.10

idon

0.96

idge

0.89

iffe

0.89

berries

0.82

unks

0.80

 Ferry

0.79

odcast

0.78

chief

0.76

pper

0.76

Activations Density 0.023%

phrases or terms related to a particular individual or proper name, possibly "Pepper" or a similar name with variations

words related to or stemming from the term "opper."

No Comments

No Known Activations