INDEX

Explanations

terms related to things or events happening in the middle or central part of something

oai_token-act-pair · gpt-3.5-turbo

terms related to specific periods or locations

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

zona

-0.81

 lawy

-0.68

abilia

-0.66

İĭ

-0.66

SCP

-0.61

 Wikipedia

-0.61

PLA

-0.61

 Scient

-0.60

 ants

-0.60

 Chamberlain

-0.60

POSITIVE LOGITS

endment

0.83

reet

0.78

imester

0.69

ãĥĵ

0.68

liction

0.66

ugh

0.64

 snack

0.64

noon

0.64

rence

0.62

Enlarge

0.62

Activations Density 0.054%

terms related to things or events happening in the middle or central part of something

terms related to specific periods or locations

No Comments

No Known Activations