INDEX

Explanations

words related to nature and the environment, particularly trees

oai_token-act-pair · gpt-3.5-turbo

nouns related to objects and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

cale

-0.75

rower

-0.73

yssey

-0.70

 Edison

-0.68

 Investor

-0.67

aurus

-0.67

 Spiel

-0.67

epad

-0.67

ync

-0.66

ndum

-0.63

POSITIVE LOGITS

lets

1.09

loads

1.07

heads

1.03

houses

1.01

blocks

1.00

tops

0.98

boats

0.95

boys

0.94

cases

0.93

 fragments

0.93

Activations Density 0.356%

words related to nature and the environment, particularly trees

nouns related to objects and structures

No Comments

No Known Activations