INDEX

Explanations

content related to media production and critique, particularly regarding length and structure

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

"},"

-0.70

conservancy

-0.65

izons

-0.64

iances

-0.64

BILITIES

-0.63

pta

-0.62

ãĢį

-0.62

gemony

-0.61

assadors

-0.60

workers

-0.59

POSITIVE LOGITS

 excerpts

1.05

 excerpt

1.05

 narrated

0.91

 narration

0.91

 reprinted

0.90

 chronological

0.89

 edited

0.88

 parody

0.85

 informative

0.85

 titled

0.85

Activations Density 0.364%

content related to media production and critique, particularly regarding length and structure

No Comments

No Known Activations