INDEX

Explanations

references to specific written or spoken material

oai_token-act-pair · gpt-3.5-turbo

relative clauses or phrases frequently starting with "that."

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

 believing

-0.61

 suspect

-0.61

idious

-0.58

say

-0.57

uty

-0.57

 persuasion

-0.56

 aversion

-0.56

abre

-0.56

OME

-0.55

 apprehension

-0.54

POSITIVE LOGITS

 accompanies

1.40

 incorporates

1.14

 utilizes

1.13

 exists

1.12

 contains

1.10

 collects

1.10

 spans

1.09

 covers

1.08

 belongs

1.07

 connects

1.06

Activations Density 0.193%

references to specific written or spoken material

relative clauses or phrases frequently starting with "that."

No Comments

No Known Activations