INDEX

Explanations

predictions or expectations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating future actions or events anticipated to occur

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Disease

-0.70

tex

-0.68

backer

-0.66

claimer

-0.64

illusion

-0.64

Interstitial

-0.64

Quantity

-0.63

roads

-0.63

ventures

-0.63

ses

-0.61

POSITIVE LOGITS

ĭ

0.75

icipated

0.71

LY

0.69

 Beir

0.66

 newsp

0.64

ħ

0.61

 plur

0.61

¶

0.60

 applause

0.58

 msec

0.57

Activations Density 0.030%

predictions or expectations

phrases indicating future actions or events anticipated to occur

No Comments

No Known Activations