INDEX

Explanations

scientific or technical terms related to assessment or measurements

oai_token-act-pair · gpt-3.5-turbo

nouns that refer to different types of constructions or modifications

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

 mosqu

-0.71

asus

-0.68

 Citiz

-0.65

tiny

-0.64

Mos

-0.64

 earthqu

-0.63

CHAR

-0.61

 subur

-0.61

Effective

-0.60

ãĥ£

-0.58

POSITIVE LOGITS

ettings

1.12

uggest

1.12

hower

1.11

hip

1.04

mith

1.03

uits

1.00

leeve

0.96

hooting

0.94

ktop

0.94

omething

0.93

Activations Density 0.118%

scientific or technical terms related to assessment or measurements

nouns that refer to different types of constructions or modifications

No Comments

No Known Activations