INDEX

Explanations

words related to movement in and out and up and down

oai_token-act-pair · gpt-3.5-turbo

phrases related to movement or transitions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

INT

-0.76

ogi

-0.75

odore

-0.74

ARE

-0.72

oir

-0.69

NAS

-0.67

MN

-0.66

Kids

-0.66

atl

-0.65

resa

-0.65

POSITIVE LOGITS

 depending

0.92

 interchange

0.82

ilaterally

0.80

 alike

0.76

etheless

0.74

 endlessly

0.74

 seamlessly

0.73

 movements

0.72

 throughout

0.71

 territ

0.71

Activations Density 0.083%

words related to movement in and out and up and down

phrases related to movement or transitions

No Comments

No Known Activations