INDEX

Explanations

words related to publications, such as "book", "article", and "chapter"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "rd" which likely denotes a type of rating or designation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Speedway

-0.76

 Kimmel

-0.75

staking

-0.74

 Katrina

-0.67

terson

-0.64

ropolis

-0.61

 Petraeus

-0.60

 Haram

-0.57

 Chow

-0.57

 relegated

-0.56

POSITIVE LOGITS

ouble

1.10

oÄŁan

0.98

yss

0.90

isl

0.88

irty

0.88

party

0.86

ividual

0.85

uces

0.84

iate

0.83

iamond

0.83

Activations Density 0.012%

words related to publications, such as "book", "article", and "chapter"

occurrences of the abbreviation "rd" which likely denotes a type of rating or designation

No Comments

No Known Activations