INDEX

Explanations

plausible explanations or justifications

oai_token-act-pair · gpt-3.5-turbo

the concept of plausibility and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

hips

-0.85

rush

-0.84

nen

-0.75

RAW

-0.75

cellence

-0.75

zona

-0.73

eg

-0.71

waters

-0.71

vals

-0.70

inals

-0.70

POSITIVE LOGITS

ausible

0.92

 excuse

0.88

 plausible

0.86

 plaus

0.81

den

0.81

 escape

0.80

 scenario

0.78

 scenarios

0.77

 conceivable

0.77

\\\\\\\\

0.77

Activations Density 0.025%

plausible explanations or justifications

the concept of plausibility and related terms

No Comments

No Known Activations