INDEX

Explanations

words related to names or nicknames.

oai_token-act-pair · gpt-3.5-turbo

references to specific cultural or media-related personalities and their roles

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

 Cortex

-0.63

 Donation

-0.63

 "$:/

-0.62

 unfocusedRange

-0.62

 Triangle

-0.61

 Refuge

-0.61

NCT

-0.60

 descend

-0.60

 Lobby

-0.59

 Odin

-0.59

POSITIVE LOGITS

rill

0.87

iland

0.85

inki

0.84

illin

0.80

chery

0.79

vity

0.77

glers

0.75

puff

0.74

opol

0.73

okia

0.73

Activations Density 0.070%

words related to names or nicknames.

references to specific cultural or media-related personalities and their roles

No Comments

No Known Activations