INDEX

Explanations

sequences of alphanumeric characters that could represent technical data or identifiers

oai_token-act-pair · gpt-3.5-turbo

numerical sequences and codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 TOUR

-0.69

 NETWORK

-0.66

 mutual

-0.62

 proverb

-0.60

ULAR

-0.60

 gears

-0.59

 Volks

-0.59

 glim

-0.57

ILA

-0.56

SHIP

-0.56

POSITIVE LOGITS

ea

1.42

cb

1.42

aea

1.38

bda

1.34

ae

1.34

bf

1.33

ffe

1.33

da

1.32

efe

1.32

fc

1.32

Activations Density 0.029%

sequences of alphanumeric characters that could represent technical data or identifiers

numerical sequences and codes

No Comments

No Known Activations