INDEX

Explanations

the word "sen" followed by a single digit

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "sen" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 heels

-0.69

Pwr

-0.69

anked

-0.66

 hitch

-0.66

tails

-0.65

 Mayweather

-0.63

cock

-0.62

 juggling

-0.61

 grounding

-0.61

 tolerance

-0.61

POSITIVE LOGITS

pai

1.55

egal

1.14

iors

1.12

seless

1.10

ocide

1.07

iture

1.05

vironment

1.04

escent

1.00

ior

0.99

ovo

0.94

Activations Density 0.018%

the word "sen" followed by a single digit

occurrences of the word "sen" and its variations in different contexts

No Comments

No Known Activations