INDEX

Explanations

proper nouns related to organizations, locations, or individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of various sources or references

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

mere

-0.74

å¥³

-0.73

coins

-0.70

ãĤ¦ãĤ¹

-0.69

alpha

-0.69

ben

-0.69

tes

-0.67

ratulations

-0.65

TEXT

-0.65

opsis

-0.65

POSITIVE LOGITS

 various

0.92

 departments

0.90

 organisations

0.87

 both

0.86

 agencies

0.83

 universities

0.81

 Various

0.80

 disparate

0.80

 academia

0.79

 organizations

0.77

Activations Density 0.197%

proper nouns related to organizations, locations, or individuals

mentions of various sources or references

No Comments

No Known Activations