INDEX

Explanations

words related to expectations or judgments of oneself or others

oai_token-act-pair · gpt-3.5-turbo

the verb "be" and its various forms, indicating a focus on existence or state of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 dispute

-0.64

 Falk

-0.57

 Frey

-0.55

Wol

-0.54

 sweat

-0.53

Wid

-0.53

 Boll

-0.53

Gum

-0.52

 Wick

-0.52

Gul

-0.51

POSITIVE LOGITS

 able

0.96

 anyways

0.88

0.83

held

0.81

.#

0.80

 anyway

0.79

 when

0.78

!!!!!!!!

0.78

!.

0.76

ecause

0.74

Activations Density 0.089%

words related to expectations or judgments of oneself or others

the verb "be" and its various forms, indicating a focus on existence or state of being

No Comments

No Known Activations

words related to expectations or judgments of oneself or others

the verb "be" and its various forms, indicating a focus on existence or state of being

No Comments

No Known Activations