INDEX

Explanations

dates in specific formats

oai_token-act-pair · gpt-3.5-turbo

periods indicating the end of statements or sentences

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

 pudding

-0.85

 fishes

-0.80

 everywhere

-0.77

 sauces

-0.76

 minion

-0.74

 hats

-0.72

 necks

-0.71

 opponent

-0.71

 instinct

-0.70

 heav

-0.70

POSITIVE LOGITS

 However

1.01

 Afterwards

0.99

 Since

0.96

 Additionally

0.95

 According

0.95

 Meanwhile

0.93

 Previously

0.92

 Presumably

0.92

 Alternatively

0.90

 Similarly

0.89

Activations Density 0.521%

dates in specific formats

periods indicating the end of statements or sentences

No Comments

No Known Activations