INDEX

Explanations

instances where imperfections are highlighted or acknowledged

oai_token-act-pair · gpt-3.5-turbo

occurrences and discussions of perfection or ideality

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

wash

-0.62

querade

-0.59

li

-0.59

appa

-0.58

 Quote

-0.57

 WARN

-0.56

@@

-0.56

 WATCH

-0.55

 brace

-0.54

POSITIVE LOGITS

 anymore

1.29

nor

1.12

 specifics

0.82

yet

0.75

necess

0.70

 necessarily

0.66

teness

0.65

yet

0.64

specific

0.63

Obj

0.62

Activations Density 0.474%

instances where imperfections are highlighted or acknowledged

occurrences and discussions of perfection or ideality

No Comments

No Known Activations