INDEX

Explanations

words related to physical actions or adjustments

oai_token-act-pair · gpt-3.5-turbo

terms related to tilting and positioning, particularly in visual or physical 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

vernment

-0.97

few

-0.88

hovah

-0.79

inventoryQuantity

-0.78

phe

-0.75

sts

-0.74

xtap

-0.74

hov

-0.72

umption

-0.71

pton

-0.68

POSITIVE LOGITS

 tripod

0.83

onomy

0.83

owl

0.81

odon

0.78

 Assist

0.71

 dock

0.70

 adapter

0.70

dragon

0.69

 tilt

0.69

 orientation

0.69

Activations Density 0.019%

words related to physical actions or adjustments

terms related to tilting and positioning, particularly in visual or physical contexts

No Comments

No Known Activations