INDEX

Explanations

terms related to the theory of evolution

oai_token-act-pair · gpt-3.5-turbo

references to the theory of evolution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

mg

-0.72

âĸ¬âĸ¬

-0.70

âĸ¬

-0.67

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.66

acht

-0.64

uster

-0.64

Prov

-0.64

Â¯Â¯

-0.63

ãģ®éŃĶ

-0.63

 Mouth

-0.63

POSITIVE LOGITS

arily

1.17

aeda

1.05

esis

0.99

 evolution

0.89

 evolve

0.88

gypt

0.87

etics

0.86

ulkan

0.81

ists

0.79

alogy

0.78

Activations Density 0.012%

terms related to the theory of evolution

references to the theory of evolution

No Comments

No Known Activations