INDEX

Explanations

words related to actively looking for something or investigating

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "search" and its variations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mos

-0.64

 pronounced

-0.60

notice

-0.59

Production

-0.59

activation

-0.58

assault

-0.57

credit

-0.57

cision

-0.56

adra

-0.55

interstitial

-0.55

POSITIVE LOGITS

 frantically

0.96

 diligently

0.89

iless

0.85

emouth

0.85

Ô

0.82

lessly

0.81

 tirelessly

0.80

 unsuccessfully

0.77

 blindly

0.76

ibly

0.74

Activations Density 0.080%

words related to actively looking for something or investigating

occurrences of the word "search" and its variations

No Comments

No Known Activations