INDEX

Explanations

technical terms and code related keywords

oai_token-act-pair · gpt-3.5-turbo

terms related to data structures or programming concepts

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

 juggling

-0.64

 anch

-0.63

 counterpart

-0.63

equ

-0.62

 Dane

-0.60

ATTLE

-0.59

 Dragonbound

-0.59

 mastering

-0.58

 flank

-0.58

 crest

-0.58

POSITIVE LOGITS

etics

0.80

ict

0.77

ĩ

0.77

eworthy

0.75

itivity

0.72

orical

0.72

alg

0.71

oir

0.71

ements

0.70

cept

0.70

Activations Density 0.299%

technical terms and code related keywords

terms related to data structures or programming concepts

No Comments

No Known Activations