INDEX

Explanations

words related to problems or issues

oai_token-act-pair · gpt-3.5-turbo

references to "problems."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

orks

-0.86

rib

-0.84

alty

-0.83

arers

-0.77

urses

-0.77

vez

-0.75

glomer

-0.74

irth

-0.73

athered

-0.72

rica

-0.72

POSITIVE LOGITS

Problem

1.18

 plag

1.02

 problem

0.97

 problems

0.91

problem

0.91

 Problem

0.90

naires

0.85

 retard

0.84

 solving

0.83

 Problems

0.82

Activations Density 0.035%

words related to problems or issues

references to "problems."

No Comments

No Known Activations