INDEX

Explanations

phrases that contain reported speech, often with the word 'said'

oai_token-act-pair · gpt-3.5-turbo

statements made by individuals in a discussion or report

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

cffffcc

-0.72

 hinge

-0.61

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.58

)—

-0.57

 harvest

-0.56

oxy

-0.55

begin

-0.55

 CrossRef

-0.54

DATA

-0.54

llular

-0.54

POSITIVE LOGITS

 sarcast

0.92

 congratulated

0.87

 applaud

0.81

 applauded

0.77

 congrat

0.76

icter

0.75

Wem

0.74

uden

0.74

 symp

0.72

 congratulations

0.72

Activations Density 0.304%

phrases that contain reported speech, often with the word 'said'

statements made by individuals in a discussion or report

No Comments

No Known Activations