INDEX

Explanations

terms related to the act of including or incorporating something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "include" and its variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sis

-0.77

©¶æ¥µ

-0.67

Ĥİ

-0.67

century

-0.66

pring

-0.66

ongyang

-0.65

Ñı

-0.64

norm

-0.63

terness

-0.63

iya

-0.63

POSITIVE LOGITS

 prominently

1.00

 elements

0.91

 disclaim

0.86

 clauses

0.85

 provisions

0.84

 references

0.81

 caveats

0.80

 quotes

0.79

 safeguards

0.78

 mention

0.76

Activations Density 0.220%

terms related to the act of including or incorporating something

instances of the word "include" and its variations

No Comments

No Known Activations