INDEX

Explanations

words related to power dynamics and manipulation

oai_token-act-pair · gpt-3.5-turbo

instances of numerical values or quantities and their implications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

intend

-0.71

angler

-0.67

appropri

-0.67

 rapt

-0.63

 respons

-0.63

rament

-0.63

 pastoral

-0.61

 vanishing

-0.60

 charm

-0.59

body

-0.59

POSITIVE LOGITS

 Explicit

0.88

 Lastly

0.76

æĺ¯

0.75

 Languages

0.75

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.74

 à¨

0.74

FORE

0.71

Ø³

0.69

anguages

0.68

Disclaimer

0.68

Activations Density 0.048%

words related to power dynamics and manipulation

instances of numerical values or quantities and their implications in various contexts

No Comments

No Known Activations