INDEX

Explanations

exceptions or contrasting information in a given context

oai_token-act-pair · gpt-3.5-turbo

terms related to exceptions, opportunities, and considerations in various contexts

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

ĺ

-0.70

ãĤ´ãĥ³

-0.65

ãĤ©

-0.63

 Picks

-0.62

his

-0.61

ãĥ¼ãĥ«

-0.61

ãĥł

-0.60

 Crate

-0.59

cedes

-0.58

buster

-0.57

POSITIVE LOGITS

 overlap

0.90

 shortage

0.86

 lurking

0.80

 waiting

0.77

 outcry

0.76

 mismatch

0.75

 somew

0.75

 difference

0.72

 unanim

0.72

 temptation

0.72

Activations Density 0.317%

exceptions or contrasting information in a given context

terms related to exceptions, opportunities, and considerations in various contexts

No Comments

No Known Activations