INDEX

Explanations

descriptions related to physical attributes or features, such as size, shape, and performance characteristics

oai_token-act-pair · gpt-3.5-turbo

various attributes and characteristics of objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĶ°

-0.61

Ĥİ

-0.60

culus

-0.59

estern

-0.59

IAL

-0.59

¯

-0.58

sein

-0.58

onica

-0.57

pps

-0.57

gart

-0.57

POSITIVE LOGITS

 contains

1.17

 lacks

1.15

 retains

1.11

 attracts

1.09

 weighs

1.09

 possesses

1.08

 employs

1.08

 generates

1.07

 incorporates

1.06

 provides

1.06

Activations Density 0.329%

descriptions related to physical attributes or features, such as size, shape, and performance characteristics

various attributes and characteristics of objects

No Comments

No Known Activations