INDEX

Explanations

verbs related to loud vocal expressions or outcries

oai_token-act-pair · gpt-3.5-turbo

instances of vocal expressions of urgency or emotion

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

folios

-0.82

folio

-0.78

algia

-0.77

uncture

-0.75

flix

-0.70

amation

-0.70

å§«

-0.67

 Democr

-0.66

nesota

-0.66

ãĥ´

-0.66

POSITIVE LOGITS

 louder

1.12

 loudly

0.99

 aloud

0.86

 shout

0.85

 slogans

0.83

 goodbye

0.83

 shouted

0.81

 yells

0.80

 shouting

0.80

 yelling

0.79

Activations Density 0.030%

verbs related to loud vocal expressions or outcries

instances of vocal expressions of urgency or emotion

No Comments

No Known Activations