INDEX

Explanations

mentions of the word "gold"

oai_token-act-pair · gpt-3.5-turbo

references to gold

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ATIONS

-0.83

ROR

-0.80

zee

-0.70

mble

-0.70

 reperto

-0.68

=-=-=-=-

-0.67

 Consent

-0.67

————————

-0.67

========

-0.66

================================================================

-0.65

POSITIVE LOGITS

 medal

1.09

vertisement

1.04

fish

1.03

smith

1.01

 coins

1.00

mine

0.93

 medals

0.93

 jewelry

0.90

stone

0.89

stones

0.84

Activations Density 0.011%

mentions of the word "gold"

references to gold

No Comments

No Known Activations