INDEX

Explanations

phrases related to being "downbeat" or feeling low or pessimistic

oai_token-act-pair · gpt-3.5-turbo

expressions of disappointment or negativity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.73

ature

-0.67

-0.66

aceous

-0.66

 Markus

-0.62

ista

-0.60

ificent

-0.60

ĸļ

-0.59

çĶ°

-0.57

 surrounds

-0.56

POSITIVE LOGITS

graded

1.32

grading

1.21

stairs

1.21

LOAD

1.14

grades

1.04

hill

1.00

played

0.97

pour

0.97

stem

0.92

loaded

0.91

Activations Density 0.040%

phrases related to being "downbeat" or feeling low or pessimistic

expressions of disappointment or negativity

No Comments

No Known Activations