INDEX

Explanations

words related to negative emotions or experiences

oai_token-act-pair · gpt-3.5-turbo

gerunds and present participles that convey emotional or descriptive states

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

nav

-0.82

endment

-0.73

ariat

-0.71

sup

-0.70

puting

-0.70

skip

-0.70

ifference

-0.68

trak

-0.67

ruary

-0.67

otiation

-0.66

POSITIVE LOGITS

ly

1.31

LY

1.09

inventoryQuantity

0.90

tons

0.87

ively

0.78

 atmosp

0.77

 visuals

0.77

NESS

0.77

 environments

0.76

 heights

0.76

Activations Density 0.155%

words related to negative emotions or experiences

gerunds and present participles that convey emotional or descriptive states

No Comments

No Known Activations