INDEX

Explanations

responses or reactions to stimuli or requests

oai_token-act-pair · gpt-3.5-turbo

instances of the word "respond."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 rumours

-0.70

 Knot

-0.68

 Dynasty

-0.66

 Guinness

-0.64

 rumors

-0.64

held

-0.61

gin

-0.59

bare

-0.59

 dynasty

-0.58

 trophies

-0.58

POSITIVE LOGITS

 respond

3.49

 responds

2.43

 responding

2.27

 responded

2.21

 response

2.14

 reply

2.09

respond

2.03

 Respond

2.01

response

1.95

 responses

1.80

Activations Density 0.016%

responses or reactions to stimuli or requests

instances of the word "respond."

No Comments

No Known Activations