INDEX

Explanations

technical terms related to physical objects and operations

oai_token-act-pair · gpt-3.5-turbo

technical terms and descriptors related to programming, engineering, and devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hops

-0.84

tics

-0.83

rencies

-0.81

 Occupations

-0.80

doms

-0.80

 establishments

-0.79

 Posts

-0.78

 Vehicles

-0.77

urches

-0.76

urrencies

-0.75

POSITIVE LOGITS

 version

0.88

 variant

0.85

 component

0.79

 identifier

0.77

 statement

0.76

 adjustment

0.75

 subscription

0.75

 lesson

0.74

 interpreter

0.74

 layer

0.73

Activations Density 0.547%

technical terms related to physical objects and operations

technical terms and descriptors related to programming, engineering, and devices

No Comments

No Known Activations