INDEX

Explanations

adjectives describing the degree or possibility of something happening

oai_token-act-pair · gpt-3.5-turbo

phrases that express potential actions or possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Continued

-0.77

oother

-0.69

NPR

-0.64

finished

-0.62

ror

-0.61

amar

-0.61

RECT

-0.60

 reassured

-0.59

iets

-0.58

 Passive

-0.58

POSITIVE LOGITS

 imaginable

1.26

 muster

0.96

 conceivable

0.91

ãĥĳ

0.82

 possibly

0.82

ãĤ«

0.79

achus

0.74

 ever

0.74

ãĥ«

0.73

 disposal

0.72

Activations Density 0.153%

adjectives describing the degree or possibility of something happening

phrases that express potential actions or possibilities

No Comments

No Known Activations