INDEX

Explanations

phrases indicating likelihood or assumption

oai_token-act-pair · gpt-3.5-turbo

statements about the occurrences or situations involving the verb "be."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FUL

-0.79

igs

-0.68

enic

-0.68

arios

-0.68

aths

-0.67

ocaust

-0.66

alez

-0.63

igible

-0.61

Sud

-0.59

orem

-0.59

POSITIVE LOGITS

 somew

0.78

 plateau

0.74

 slowing

0.71

 forgotten

0.70

 circling

0.69

 dividing

0.69

 suppl

0.69

 stalled

0.69

 overlooked

0.69

 stagn

0.68

Activations Density 0.141%

phrases indicating likelihood or assumption

statements about the occurrences or situations involving the verb "be."

No Comments

No Known Activations