INDEX

Explanations

numerical values or technical terms within code snippets

oai_token-act-pair · gpt-3.5-turbo

terms related to updates and changes in systems or processes

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

otta

-0.56

omorphic

-0.53

anova

-0.51

Brit

-0.50

ammad

-0.50

natureconservancy

-0.48

 hating

-0.45

olitical

-0.45

nick

-0.45

root

-0.44

POSITIVE LOGITS

nesday

0.50

 Schultz

0.48

 Collider

0.47

 guiName

0.46

 Destination

0.45

enment

0.45

 Base

0.45

 Wonderland

0.45

eatures

0.45

atche

0.45

Activations Density 1.423%

numerical values or technical terms within code snippets

terms related to updates and changes in systems or processes

No Comments

No Known Activations