INDEX

Explanations

phrases related to spinning or rotation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "spinning" 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 @ 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

alty

-0.79

-0.76

éĹĺ

-0.71

bour

-0.71

orers

-0.70

artment

-0.70

put

-0.69

ãģ®å

-0.67

eq

-0.67

irez

-0.66

POSITIVE LOGITS

irling

0.98

 spinning

0.97

 weaving

0.88

 spins

0.86

 slic

0.84

tails

0.83

 vortex

0.83

ernaut

0.82

 spun

0.80

lass

0.80

Activations Density 0.045%

phrases related to spinning or rotation

occurrences of the word "spinning" and its variations

No Comments

No Known Activations