INDEX

Explanations

the name "Si" with varying levels of emphasis or context

oai_token-act-pair · gpt-3.5-turbo

repeated mentions or instances of the term "Si" in various contexts

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

lain

-0.94

ãĥ¼ãĥĨ

-0.89

eers

-0.84

eer

-0.75

theless

-0.75

edly

-0.69

tenance

-0.67

 Kessler

-0.67

liness

-0.65

£ı

-0.64

POSITIVE LOGITS

enna

1.02

pling

1.02

plin

0.96

ames

0.94

inx

0.93

ada

0.87

uan

0.87

Si

0.86

ples

0.86

RNA

0.84

Activations Density 0.017%

the name "Si" with varying levels of emphasis or context

repeated mentions or instances of the term "Si" in various contexts

No Comments

No Known Activations