INDEX

Explanations

the frequency or repetition of the word "many" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.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

UAL

-0.76

anut

-0.73

icism

-0.71

OPE

-0.69

agame

-0.68

istan

-0.67

ngth

-0.67

oulos

-0.65

atum

-0.65

ACTED

-0.64

POSITIVE LOGITS

 facets

1.09

 times

1.04

 aspects

1.02

 thousands

0.94

 kinds

0.94

 different

0.93

body

0.86

 thousand

0.86

 unanswered

0.85

 occasions

0.85

Activations Density 0.067%

the frequency or repetition of the word "many" in different contexts

No Comments

No Known Activations