INDEX

Explanations

words related to hope and positivity

oai_token-act-pair · gpt-3.5-turbo

references to hope

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

cise

-0.79

pes

-0.76

entin

-0.71

insula

-0.68

Interstitial

-0.68

cers

-0.67

versions

-0.66

vet

-0.64

pta

-0.64

çİĭ

-0.63

POSITIVE LOGITS

lessly

1.08

fulness

0.90

 hope

0.82

eful

0.78

lessness

0.77

fully

0.75

 hopeful

0.72

bringer

0.71

 Hicks

0.70

FUL

0.70

Activations Density 0.027%

words related to hope and positivity

references to hope

No Comments

No Known Activations