INDEX

Explanations

phrases related to certainty or belief, indicating possible doubt or validation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating certainty or truthfulness

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

ngth

-0.86

izabeth

-0.77

afia

-0.76

umbnails

-0.73

elve

-0.69

 hail

-0.68

quartered

-0.68

pick

-0.64

 Slay

-0.63

ichever

-0.63

POSITIVE LOGITS

 happening

1.16

 occurring

0.87

 happen

0.87

 happ

0.86

true

0.82

 happened

0.82

 untrue

0.77

 accomplished

0.77

 achievable

0.76

 unintentional

0.76

Activations Density 0.300%

phrases related to certainty or belief, indicating possible doubt or validation

phrases indicating certainty or truthfulness

No Comments

No Known Activations