INDEX

Explanations

phrases related to proving or demonstrating something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "prove" and its variations, focusing on concepts of validation and ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 newsletters

-0.71

 externalToEVAOnly

-0.69

ummer

-0.69

 livest

-0.68

cffffcc

-0.67

 contrace

-0.66

letal

-0.64

 sched

-0.63

ufact

-0.63

Osc

-0.62

POSITIVE LOGITS

biz

0.79

ance

0.78

ificate

0.74

 hypotheses

0.74

 innocence

0.73

 authenticity

0.72

reader

0.72

 Feldman

0.71

proof

0.71

worthiness

0.71

Activations Density 0.040%

phrases related to proving or demonstrating something

instances of the word "prove" and its variations, focusing on concepts of validation and ownership

No Comments

No Known Activations