INDEX

Explanations

mentions of specific holidays

oai_token-act-pair · gpt-3.5-turbo

occurrences of possessive nouns, specifically related to various holidays and cultural 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

selves

-0.90

VICE

-0.80

ahon

-0.80

hari

-0.79

unda

-0.77

Downloadha

-0.77

requ

-0.77

lled

-0.75

obin

-0.75

ilty

-0.75

POSITIVE LOGITS

 Landing

0.97

 Disease

0.96

 Island

0.91

 Gate

0.88

 Mansion

0.88

 Place

0.88

Day

0.85

 Counsel

0.82

 Angels

0.80

 Picks

0.79

Activations Density 0.058%

mentions of specific holidays

occurrences of possessive nouns, specifically related to various holidays and cultural references

No Comments

No Known Activations