INDEX

Explanations

phrases mentioning probabilities or likelihoods in a context

oai_token-act-pair · gpt-3.5-turbo

phrases related to probabilities or odds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

afort

-0.87

TPP

-0.77

artney

-0.77

Materials

-0.75

anie

-0.72

illin

-0.71

uala

-0.70

tein

-0.70

VK

-0.69

PB

-0.69

POSITIVE LOGITS

 odds

0.97

llor

0.75

 ratio

0.74

 against

0.73

 athlet

0.71

manship

0.71

 ratios

0.70

 worsh

0.69

 Whedon

0.68

busters

0.68

Activations Density 0.012%

phrases mentioning probabilities or likelihoods in a context

phrases related to probabilities or odds

No Comments

No Known Activations