INDEX

Explanations

questions beginning with 'Asked'

oai_token-act-pair · gpt-3.5-turbo

repeated phrases starting with the word "Asked."

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

audi

-0.73

cutting

-0.71

lim

-0.70

react

-0.69

ulz

-0.67

ordinate

-0.64

EMA

-0.64

lay

-0.62

marine

-0.60

analysis

-0.60

POSITIVE LOGITS

 Questions

1.09

 questions

1.08

 Asked

1.08

 asked

1.04

 rhet

0.96

Asked

0.94

 questioned

0.89

 answ

0.88

naires

0.88

 asks

0.87

Activations Density 0.010%

questions beginning with 'Asked'

repeated phrases starting with the word "Asked."

No Comments

No Known Activations