INDEX

Explanations

statements relating to learning, knowledge, feelings, and attitudes towards various subjects

oai_token-act-pair · gpt-3.5-turbo

expressions of learning, emotions, and desires

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

su

-0.72

press

-0.69

eli

-0.68

Attempt

-0.67

stru

-0.66

weed

-0.66

cele

-0.65

cephal

-0.64

oug

-0.64

intend

-0.63

POSITIVE LOGITS

 theirs

0.83

 them

0.83

 something

0.82

 THEM

0.78

 hers

0.77

 nothing

0.74

ļé

0.74

 lots

0.73

 everything

0.73

 plenty

0.71

Activations Density 0.372%

statements relating to learning, knowledge, feelings, and attitudes towards various subjects

expressions of learning, emotions, and desires

No Comments

No Known Activations