INDEX

Explanations

periods within lists of software-related descriptions or functionalities

oai_token-act-pair · gpt-3.5-turbo

decimal numbers or numeric values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 purse

-0.80

 striking

-0.68

amy

-0.68

 burglary

-0.67

 shutter

-0.67

 framing

-0.67

 alarming

-0.66

 worsh

-0.66

 involuntary

-0.65

 cradle

-0.64

POSITIVE LOGITS

1.09

1.08

jpg

0.96

0.95

0.93

dll

0.92

txt

0.92

0.90

Activations Density 0.101%

periods within lists of software-related descriptions or functionalities

decimal numbers or numeric values

No Comments

No Known Activations