INDEX

Explanations

phrases related to the process of learning

oai_token-act-pair · gpt-3.5-turbo

instances of the word "learned" or its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

govtrack

-0.67

heads

-0.62

dq

-0.61

oscope

-0.61

ordered

-0.61

lished

-0.61

ataka

-0.61

cise

-0.60

pei

-0.60

abwe

-0.60

POSITIVE LOGITS

 lessons

0.89

 firsthand

0.88

 lesson

0.84

 Curve

0.81

 humility

0.79

itudinal

0.77

 Teach

0.76

llor

0.75

learn

0.71

 learnt

0.71

Activations Density 0.046%

phrases related to the process of learning

instances of the word "learned" or its variations

No Comments

No Known Activations