INDEX

Explanations

terms related to difficulty or challenges

oai_token-act-pair · gpt-3.5-turbo

terms related to challenges or difficulties, particularly in the context of hardline ideologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 guiActiveUn

-0.79

çīĪ

-0.74

Spons

-0.74

 Neuroscience

-0.72

GD

-0.71

 rall

-0.71

minus

-0.68

rav

-0.67

Stars

-0.66

sup

-0.66

POSITIVE LOGITS

 imagine

0.71

 brush

0.68

aiman

0.67

 guess

0.63

 abras

0.61

 gauge

0.61

ody

0.60

ĵĺ

0.60

 envision

0.59

 anywhere

0.59

Activations Density 0.151%

terms related to difficulty or challenges

terms related to challenges or difficulties, particularly in the context of hardline ideologies

No Comments

No Known Activations