INDEX

Explanations

words related to upward movement or direction

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "up."

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

âĸ¬âĸ¬

-0.65

mia

-0.59

 Emanuel

-0.58

å£«

-0.58

Synopsis

-0.58

 understatement

-0.58

 scapego

-0.57

 keyword

-0.56

Closure

-0.56

Â¯Â¯Â¯Â¯

-0.55

POSITIVE LOGITS

stairs

1.10

rights

1.02

river

0.97

stage

0.89

 stairs

0.87

raised

0.86

ris

0.84

np

0.81

ornia

0.81

erd

0.80

Activations Density 0.077%

words related to upward movement or direction

occurrences of the word "up."

No Comments

No Known Activations