INDEX

Explanations

terms related to specific locations or entities, such as cities, countries, and organizations

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations and political entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ebin

-0.56

`.

-0.56

'.

-0.54

etimes

-0.54

').

-0.51

"]=>

-0.51

onyms

-0.50

 nodd

-0.50

ktop

-0.49

ãĤ¢ãĥ«

-0.48

POSITIVE LOGITS

1.12

,[

1.00

,,

0.95

Â®,

0.94

*,

0.93

?,

0.84

(),

0.82

,...

0.81

!,

0.81

Activations Density 0.545%

terms related to specific locations or entities, such as cities, countries, and organizations

references to geographical locations and political entities

No Comments

No Known Activations