INDEX

Explanations

expressions of apology or sympathy

oai_token-act-pair · gpt-3.5-turbo

instances of the word "sorry."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

tnc

-0.77

Ranked

-0.76

egal

-0.69

kefeller

-0.69

sports

-0.69

psey

-0.68

ccording

-0.68

eele

-0.66

irrel

-0.65

iltration

-0.65

POSITIVE LOGITS

 sorry

1.04

 excuse

0.95

GES

0.85

sorry

0.80

Sorry

0.79

giving

0.76

tm

0.75

 guys

0.74

 apologies

0.73

 pardon

0.73

Activations Density 0.015%

expressions of apology or sympathy

instances of the word "sorry."

No Comments

No Known Activations