INDEX

Explanations

conjunctions followed by contractions

oai_token-act-pair · gpt-3.5-turbo

the phrase "let's" 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 @ 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

ELD

-0.79

rupted

-0.70

eur

-0.69

 surrounds

-0.65

 Deaths

-0.65

rupt

-0.60

ãĥĨ

-0.60

velop

-0.59

abytes

-0.59

IED

-0.58

POSITIVE LOGITS

 suppose

0.97

 gotta

0.91

 assume

0.91

 gonna

0.90

 pretend

0.86

 speculate

0.83

got

0.82

 settle

0.81

get

0.79

 presume

0.78

Activations Density 0.023%

conjunctions followed by contractions

the phrase "let's" in various contexts

No Comments

No Known Activations