INDEX

Explanations

Phrases indicating similarity or agreement

oai_token-act-pair · gpt-3.5-turbo

references to the concept of sameness or doing something similar

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Leilan

-0.77

hens

-0.63

 Married

-0.63

 frag

-0.58

uble

-0.56

GSL

-0.55

 casts

-0.55

 squash

-0.54

UST

-0.54

SD

-0.54

POSITIVE LOGITS

 thing

0.81

 fate

0.79

 anecd

0.77

emetery

0.77

^^^^

0.73

retch

0.71

.<

0.69

.</

0.69

 feat

0.69

Activations Density 0.159%

Phrases indicating similarity or agreement

references to the concept of sameness or doing something similar

No Comments

No Known Activations