INDEX

Explanations

terms related to research, studies, and findings

oai_token-act-pair · gpt-3.5-turbo

patterns and relationships involving data or statistics

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

soever

-0.77

lr

-0.76

ç¥ŀ

-0.75

Reviewed

-0.70

issance

-0.65

Nir

-0.64

 Beard

-0.63

 Secondly

-0.59

ensor

-0.59

ãĥĥ

-0.58

POSITIVE LOGITS

 similarities

0.86

actly

0.85

 discrepancies

0.76

 discrepancy

0.72

 resemblance

0.70

 similarity

0.67

 anomalies

0.67

 overlap

0.67

TextColor

0.66

 irregularities

0.65

Activations Density 0.601%

terms related to research, studies, and findings

patterns and relationships involving data or statistics

No Comments

No Known Activations