INDEX

Explanations

time-related terms indicating quick actions or responses

oai_token-act-pair · gpt-3.5-turbo

time-related phrases and durations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pri

-0.65

Values

-0.61

apego

-0.61

oren

-0.61

odynam

-0.60

 SOLD

-0.59

Neg

-0.59

 Baal

-0.59

acus

-0.58

atu

-0.57

POSITIVE LOGITS

 increments

0.89

 radius

0.83

 confines

0.79

eme

0.74

hrs

0.72

aneously

0.72

 vicinity

0.71

ombat

0.71

 timeframe

0.70

noon

0.69

Activations Density 0.072%

time-related terms indicating quick actions or responses

time-related phrases and durations

No Comments

No Known Activations