INDEX

Explanations

phrases indicating recommendations or suggestions

oai_token-act-pair · gpt-3.5-turbo

statements of fact or assertions about conditions or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 wills

-0.66

itches

-0.64

 elders

-0.63

peg

-0.62

 encounters

-0.61

urry

-0.60

 senses

-0.60

 floats

-0.59

aturdays

-0.59

 notices

-0.59

POSITIVE LOGITS

rael

1.14

nt

1.00

cussion

0.97

olation

0.95

 definitely

0.91

senal

0.87

olate

0.87

 indeed

0.85

 ALWAYS

0.85

 certainly

0.82

Activations Density 0.638%

phrases indicating recommendations or suggestions

statements of fact or assertions about conditions or qualities

No Comments

No Known Activations