INDEX

Explanations

verbs in the past tense that describe actions or states

oai_token-act-pair · gpt-3.5-turbo

words associated with actions or conditions in a relational context

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

illian

-0.57

ãĥ©ãĥ³

-0.55

 crowdfunding

-0.55

 Gamble

-0.54

 Bauer

-0.52

ILA

-0.52

 GoPro

-0.51

cuts

-0.51

ican

-0.51

 Kills

-0.51

POSITIVE LOGITS

 uncond

0.95

 incorrectly

0.84

 correctly

0.82

 improperly

0.82

 indirectly

0.82

 separately

0.80

 irrespective

0.80

 prematurely

0.79

itionally

0.79

 manually

0.78

Activations Density 0.328%

verbs in the past tense that describe actions or states

words associated with actions or conditions in a relational context

No Comments

No Known Activations