INDEX

Explanations

lists of items or actions

oai_token-act-pair · gpt-3.5-turbo

common conjunctions or phrases in a list format

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

ļéĨĴ

-0.78

Reward

-0.67

interstitial

-0.65

ername

-0.65

quist

-0.61

DERR

-0.61

 enthusi

-0.59

abo

-0.59

ãĤ´ãĥ³

-0.58

oe

-0.57

POSITIVE LOGITS

huh

1.34

 meanwhile

1.02

eh

1.02

etc

0.96

 however

0.91

yes

0.91

 yeah

0.86

 please

0.81

sir

0.81

 alas

0.80

Activations Density 0.377%

lists of items or actions

common conjunctions or phrases in a list format

No Comments

No Known Activations