INDEX

Explanations

phrases related to changes, developments, or conditions that are noteworthy or indicative of a specific state

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to signs or indications of various conditions or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

quet

-0.80

eah

-0.74

chens

-0.74

ials

-0.73

nets

-0.72

adelphia

-0.71

omers

-0.71

apest

-0.69

ourses

-0.69

iband

-0.69

POSITIVE LOGITS

 decay

0.88

 bias

0.77

 fatigue

0.77

 aggression

0.74

 occupancy

0.74

 warmth

0.74

 distress

0.73

 desperation

0.72

 progress

0.71

 differentiation

0.71

Activations Density 0.056%

phrases related to changes, developments, or conditions that are noteworthy or indicative of a specific state

phrases that refer to signs or indications of various conditions or situations

No Comments

No Known Activations