INDEX

Explanations

phrases related to physical movements or actions

oai_token-act-pair · gpt-3.5-turbo

sentences that conclude with a period

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

omics

-0.98

 defe

-0.84

 affili

-0.83

uly

-0.82

 volunte

-0.81

 entreprene

-0.79

iber

-0.78

 royalty

-0.76

 discounted

-0.76

 quir

-0.75

POSITIVE LOGITS

 Afterwards

1.13

 Additionally

1.07

 Each

1.05

 Likewise

1.05

 Luckily

1.05

 Fortunately

1.05

 However

1.03

 Meanwhile

1.03

 Alternatively

1.03

 Similarly

1.02

Activations Density 0.749%

phrases related to physical movements or actions

sentences that conclude with a period

No Comments

No Known Activations