INDEX

Explanations

words related to technology and discussions

oai_token-act-pair · gpt-3.5-turbo

symbols that are repeated or signify an important element

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 spiral

-0.72

 sidx

-0.68

uyomi

-0.66

 Barrier

-0.64

OTOS

-0.64

 Shroud

-0.64

 Phant

-0.63

è£ħ

-0.62

 Saga

-0.61

 Downs

-0.61

POSITIVE LOGITS

say

0.82

cause

0.80

which

0.80

then

0.79

especially

0.77

his

0.77

º

0.74

said

0.74

£

0.74

inion

0.74

Activations Density 0.121%

words related to technology and discussions

symbols that are repeated or signify an important element

No Comments

No Known Activations