INDEX

Explanations

verbs related to forceful or determined actions

oai_token-act-pair · gpt-3.5-turbo

words related to processes of growth or movement

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

 Cust

-0.75

Journal

-0.73

xus

-0.73

cius

-0.67

 Registered

-0.63

ensis

-0.63

Veter

-0.59

 Compar

-0.59

clusive

-0.58

Phys

-0.58

POSITIVE LOGITS

ãĥ³ãĤ¸

0.76

ctl

0.73

ãĥ¼

0.73

ards

0.72

itzer

0.72

stone

0.70

imeters

0.68

mann

0.68

 acre

0.67

Ðµ

0.66

Activations Density 0.028%

verbs related to forceful or determined actions

words related to processes of growth or movement

No Comments

No Known Activations