INDEX

Explanations

the word "uss" with different activation levels

oai_token-act-pair · gpt-3.5-turbo

the term "uss" in various contexts throughout the document

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

 lull

-0.61

 LIFE

-0.60

 turf

-0.60

 Arbor

-0.59

ISA

-0.59

 stock

-0.59

 halftime

-0.58

 potency

-0.57

 crest

-0.57

 identical

-0.56

POSITIVE LOGITS

alam

1.09

engers

1.09

uss

1.08

ault

1.03

olini

0.98

enger

0.96

enegger

0.96

essor

0.93

es

0.91

enge

0.90

Activations Density 0.009%

the word "uss" with different activation levels

the term "uss" in various contexts throughout the document

No Comments

No Known Activations