INDEX

Explanations

instances where something is being modified or adjusted in some way

oai_token-act-pair · gpt-3.5-turbo

phrases related to changes or adjustments made to things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĥīãĥ©

-0.77

vice

-0.69

urus

-0.65

-0.61

ãĥĪ

-0.61

 haunt

-0.59

inar

-0.59

ublic

-0.58

Champ

-0.58

netflix

-0.57

POSITIVE LOGITS

 considerably

1.25

 slightly

1.10

 greatly

1.02

 further

1.01

 accordingly

1.01

 substantially

0.99

 drastically

0.96

 sufficiently

0.95

 significantly

0.94

 dramatically

0.92

Activations Density 0.345%

instances where something is being modified or adjusted in some way

phrases related to changes or adjustments made to things

No Comments

No Known Activations