INDEX

Explanations

personal anecdotes or statements starting with "My"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "My" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

itect

-0.70

itud

-0.68

Ø³

-0.66

-0.65

OPLE

-0.65

 Frieza

-0.65

ciation

-0.65

Balt

-0.64

PTS

-0.62

 Edison

-0.61

POSITIVE LOGITS

anmar

1.28

stery

1.28

riad

1.10

self

1.09

own

1.06

ths

1.05

 apologies

1.02

stic

1.01

croft

0.98

opia

0.97

Activations Density 0.066%

personal anecdotes or statements starting with "My"

occurrences of the word "My" and its variants

No Comments

No Known Activations