INDEX

Explanations

numbers and comparisons related to levels or values, such as falling below specific thresholds or above certain amounts

oai_token-act-pair · gpt-3.5-turbo

references to thresholds and levels of measurement, particularly those that indicate being above or below certain values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

mail

-0.76

vic

-0.75

BUG

-0.71

 differently

-0.64

uid

-0.63

ado

-0.63

gmail

-0.59

dll

-0.58

RAW

-0.58

atto

-0.57

POSITIVE LOGITS

 expectations

1.02

 subsistence

0.88

 optimum

0.86

 saturation

0.85

 equilibrium

0.84

normal

0.81

 normal

0.81

 expectation

0.81

 thresholds

0.81

 peak

0.80

Activations Density 0.185%

numbers and comparisons related to levels or values, such as falling below specific thresholds or above certain amounts

references to thresholds and levels of measurement, particularly those that indicate being above or below certain values

No Comments

No Known Activations