INDEX

Explanations

words related to coding and programming

oai_token-act-pair · gpt-3.5-turbo

descriptions of Pokémon characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Borders

-0.72

 Fundamental

-0.62

 Chatt

-0.60

 Oval

-0.60

 dividing

-0.59

 Standing

-0.59

 Inspection

-0.59

 internationally

-0.57

 Cabinet

-0.57

 Fourth

-0.56

POSITIVE LOGITS

isoft

0.82

0.79

malink

0.78

ickr

0.78

soft

0.77

scribe

0.77

amel

0.76

rx

0.76

etheus

0.76

ip

0.75

Activations Density 0.255%

words related to coding and programming

descriptions of Pokémon characters

No Comments

No Known Activations