INDEX

Explanations

instances where the word "listening" is mentioned

oai_token-act-pair · gpt-3.5-turbo

instances of listening or attention directed towards various subjects or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

recy

-0.82

hra

-0.79

hesion

-0.77

 shading

-0.72

~~~~~~~~

-0.72

gradient

-0.70

shield

-0.69

ãĤ¢ãĥ«

-0.67

istan

-0.66

availability

-0.66

POSITIVE LOGITS

 podcasts

1.30

 audi

1.13

 recordings

1.09

 music

1.09

 voices

1.05

 audio

1.02

 Voices

1.01

 speeches

0.98

 conversations

0.96

 tapes

0.96

Activations Density 0.053%

instances where the word "listening" is mentioned

instances of listening or attention directed towards various subjects or activities

No Comments

No Known Activations