INDEX

Explanations

specific entities or concepts related to technology or science

oai_token-act-pair · gpt-3.5-turbo

terms related to various scientific concepts and measurements

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

rawdownloadcloneembedreportprint

-0.70

-0.68

wise

-0.65

\\\\\\\\

-0.65

cipled

-0.64

inion

-0.64

VIEW

-0.64

ATH

-0.63

rie

-0.61

special

-0.60

POSITIVE LOGITS

etter

1.21

etting

1.15

mith

1.09

heet

0.98

cape

0.94

ettings

0.93

cale

0.89

hips

0.87

chool

0.87

hirt

0.82

Activations Density 0.582%

specific entities or concepts related to technology or science

terms related to various scientific concepts and measurements

No Comments

No Known Activations