INDEX

Explanations

phrases related to doing one's best or making an effort

oai_token-act-pair · gpt-3.5-turbo

phrases expressing capability or potential actions

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

Lis

-0.65

 Politics

-0.63

 Cance

-0.63

 Mour

-0.63

 Passage

-0.63

 Falk

-0.63

Ez

-0.62

 Prin

-0.62

 Rising

-0.61

 Falling

-0.61

POSITIVE LOGITS

berra

1.05

't

1.04

 muster

1.04

 feas

0.93

adian

0.86

 reasonably

0.84

nesota

0.82

 afford

0.81

iary

0.79

NOT

0.79

Activations Density 0.094%

phrases related to doing one's best or making an effort

phrases expressing capability or potential actions

No Comments

No Known Activations