INDEX

Explanations

proper nouns and hypothetical situations starting with "Had."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Had" in various contexts

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

FTWARE

-0.81

 outp

-0.69

oshenko

-0.67

 scrimmage

-0.64

 pept

-0.62

 glove

-0.61

 honoring

-0.59

 tomat

-0.58

 hars

-0.57

 extingu

-0.56

POSITIVE LOGITS

iths

0.93

hers

0.92

rien

0.91

ibur

0.91

ith

0.88

rons

0.85

vard

0.85

rontal

0.84

bro

0.82

luck

0.82

Activations Density 0.074%

proper nouns and hypothetical situations starting with "Had."

instances of the word "Had" in various contexts

No Comments

No Known Activations