INDEX

Explanations

technical terms related to computer systems or procedures

oai_token-act-pair · gpt-3.5-turbo

terms related to databases and computing concepts

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

ECA

-0.68

 Been

-0.67

actionDate

-0.67

ornia

-0.65

 Posted

-0.65

 Mean

-0.64

 Earlier

-0.64

ilipp

-0.63

cellence

-0.62

?????-

-0.62

POSITIVE LOGITS

 loses

1.54

 receives

1.52

 retains

1.51

 stays

1.48

 behaves

1.48

 absorbs

1.45

 reacts

1.40

 responds

1.38

 learns

1.38

 gets

1.38

Activations Density 0.395%

technical terms related to computer systems or procedures

terms related to databases and computing concepts

No Comments

No Known Activations