INDEX

Explanations

phrases describing a strong or dominant characteristic

oai_token-act-pair · gpt-3.5-turbo

phrases and terms relating to generalizations or common themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

utics

-0.82

!.

-0.82

apons

-0.75

=]

-0.74

*.

-0.74

`.

-0.74

ilaterally

-0.73

ustom

-0.72

Ò

-0.72

ensis

-0.71

POSITIVE LOGITS

 assumption

1.19

 implication

1.17

 irony

1.16

 rationale

1.14

 question

1.14

 explanation

1.08

 impetus

1.06

 answer

1.02

 goal

1.02

 motto

1.00

Activations Density 0.337%

phrases describing a strong or dominant characteristic

phrases and terms relating to generalizations or common themes

No Comments

No Known Activations