INDEX

Explanations

phrases or terms related to the prefix "ph-"

oai_token-act-pair · gpt-3.5-turbo

words related to physical conditions or phobias

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

éĹĺ

-1.02

HCR

-0.82

âĸ¬âĸ¬

-0.78

nings

-0.74

 fitting

-0.72

Interstitial

-0.70

fit

-0.69

 shortened

-0.69

ndra

-0.69

 Chosen

-0.67

POSITIVE LOGITS

antom

1.36

oenix

1.36

ysics

1.28

ilipp

1.25

araoh

1.21

obia

1.21

allic

1.13

asing

1.12

inx

1.12

ases

1.11

Activations Density 0.018%

phrases or terms related to the prefix "ph-"

words related to physical conditions or phobias

No Comments

No Known Activations