INDEX

Explanations

phrases starting with "Imagine" followed by a scenario or action

oai_token-act-pair · gpt-3.5-turbo

instances of the word "imagine" and its variations

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

bard

-0.78

ged

-0.74

inals

-0.71

wa

-0.69

ldon

-0.65

die

-0.63

cific

-0.62

[+

-0.61

orie

-0.60

orne

-0.60

POSITIVE LOGITS

ĸļ

0.96

lihood

0.85

ufact

0.77

orial

0.76

 imagine

0.73

 aloud

0.71

 anew

0.70

 msec

0.67

how

0.67

 imagining

0.67

Activations Density 0.030%

phrases starting with "Imagine" followed by a scenario or action

instances of the word "imagine" and its variations

No Comments

No Known Activations