INDEX

Explanations

descriptions of physical environments and their features

oai_token-act-pair · gpt-3.5-turbo

phrases describing actions or states that involve physical surroundings and interactions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é¾įåĸļå£«

-0.66

ãĥ´ãĤ¡

-0.63

ONSORED

-0.63

NES

-0.62

EVA

-0.61

APTER

-0.61

alion

-0.60

çĶ°

-0.58

ERO

-0.58

Ô

-0.57

POSITIVE LOGITS

 abound

0.78

 everywhere

0.62

 prolifer

0.60

 populate

0.59

hots

0.59

 favour

0.56

 themselves

0.56

 favor

0.55

 plentiful

0.55

 roam

0.54

Activations Density 0.993%

descriptions of physical environments and their features

phrases describing actions or states that involve physical surroundings and interactions

No Comments

No Known Activations