INDEX

Explanations

phrases indicating completion or finality

oai_token-act-pair · gpt-3.5-turbo

references to actions or states of being that imply a result or consequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

igmat

-0.70

ãĥł

-0.61

ãĥķãĤ¡

-0.60

ars

-0.57

weeney

-0.56

phans

-0.55

uts

-0.55

cific

-0.55

acerb

-0.55

Pers

-0.54

POSITIVE LOGITS

 gladly

1.03

 alright

0.88

 instantly

0.79

 breeze

0.79

brainer

0.76

 amen

0.74

 effortlessly

0.73

bye

0.72

 automatically

0.72

bye

0.70

Activations Density 1.079%

phrases indicating completion or finality

references to actions or states of being that imply a result or consequence

No Comments

No Known Activations