INDEX

Explanations

symbol combinations representing a specific notation or instruction

oai_token-act-pair · gpt-3.5-turbo

contractions indicating negation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 decomp

-0.70

 contradictions

-0.70

 minim

-0.70

GPS

-0.69

cob

-0.69

gib

-0.68

çīĪ

-0.68

 shack

-0.67

 snacks

-0.67

 recording

-0.66

POSITIVE LOGITS

Ĵ

1.25

Ļ

1.15

¬

1.09

¤

1.08

£

1.08

¡

1.07

Ķ

1.07

ĵ

1.04

ĳ

1.04

İ

1.01

Activations Density 0.253%

symbol combinations representing a specific notation or instruction

contractions indicating negation

No Comments

No Known Activations