INDEX

Explanations

the word "Mend"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Mend" and its variations

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

ngth

-0.74

ãģĦ

-0.74

Leary

-0.70

 backpack

-0.66

Jane

-0.66

 Columb

-0.65

pants

-0.64

ãĥīãĥ©ãĤ´ãĥ³

-0.61

piring

-0.60

OAD

-0.60

POSITIVE LOGITS

 Mend

1.04

enh

1.02

ril

0.89

iola

0.87

oÄŁ

0.87

ez

0.86

 Mechdragon

0.81

ford

0.80

rov

0.80

rod

0.79

Activations Density 0.005%

the word "Mend"

occurrences of the name "Mend" and its variations

No Comments

No Known Activations