INDEX

Explanations

declarations or information related to research results

oai_token-act-pair · gpt-3.5-turbo

mentions of "results" or related references to data outcomes

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

resent

-0.71

nt

-0.67

 actionGroup

-0.65

afort

-0.65

 Passage

-0.65

kers

-0.64

 vows

-0.64

ker

-0.62

conservancy

-0.61

 vigil

-0.61

POSITIVE LOGITS

results

0.84

iments

0.83

 results

0.80

iveness

0.78

 Results

0.73

amples

0.73

ĸļ

0.70

ample

0.69

ivity

0.68

 thereof

0.68

Activations Density 0.030%

declarations or information related to research results

mentions of "results" or related references to data outcomes

No Comments

No Known Activations