INDEX

Explanations

words related to a specific name "Cast"

oai_token-act-pair · gpt-3.5-turbo

instances of the name "Castillo."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

vironment

-1.14

Downloadha

-0.85

£ı

-0.79

iversal

-0.77

ĸļ

-0.73

xtap

-0.68

 proble

-0.68

IGH

-0.67

ãģį

-0.66

Wem

-0.66

POSITIVE LOGITS

Cast

1.17

lev

1.05

 Cast

0.99

aways

0.99

lest

0.98

members

0.91

aign

0.91

let

0.88

member

0.85

away

0.84

Activations Density 0.008%

words related to a specific name "Cast"

instances of the name "Castillo."

No Comments

No Known Activations