INDEX

Explanations

instances where something is happening or occurring in a sequence of events

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate temporal sequences or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

itably

-0.71

 cared

-0.66

________________________________________________________________

-0.64

 bends

-0.63

 preserves

-0.60

Occ

-0.59

iol

-0.59

Located

-0.59

('

-0.59

ios

-0.59

POSITIVE LOGITS

 controversy

0.81

 controversies

0.79

 revelations

0.77

 consultations

0.76

 scathing

0.75

 Butt

0.71

 discussions

0.70

anmar

0.70

 contentious

0.70

Pew

0.69

Activations Density 0.164%

instances where something is happening or occurring in a sequence of events

phrases that indicate temporal sequences or occurrences

No Comments

No Known Activations