INDEX

Explanations

phrases indicating probability or likelihood

oai_token-act-pair · gpt-3.5-turbo

statements about likelihoods or probabilities 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rief

-0.77

aan

-0.77

arius

-0.75

inth

-0.74

andan

-0.71

ilts

-0.70

gian

-0.70

zeb

-0.70

leck

-0.70

illation

-0.68

POSITIVE LOGITS

cffff

0.81

 ingred

0.76

 likely

0.76

 elector

0.76

 releg

0.74

 infer

0.74

onna

0.70

 underestimate

0.68

 culprit

0.67

 elim

0.67

Activations Density 0.022%

phrases indicating probability or likelihood

statements about likelihoods or probabilities in various contexts

No Comments

No Known Activations