INDEX

Explanations

locations or actions related to pipelines

oai_token-act-pair · gpt-3.5-turbo

specific geographical locations or names associated with certain contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

hirt

-0.84

ettings

-0.72

OAD

-0.72

cases

-0.71

çīĪ

-0.66

cloth

-0.64

astical

-0.64

ctrl

-0.63

faces

-0.62

getic

-0.62

POSITIVE LOGITS

elines

0.82

estine

0.81

ership

0.78

env

0.74

eful

0.72

imately

0.72

ocry

0.72

 disarm

0.70

imet

0.70

olen

0.70

Activations Density 0.025%

locations or actions related to pipelines

specific geographical locations or names associated with certain contexts

No Comments

No Known Activations