INDEX

Explanations

specific phrases indicating being tied or connected

oai_token-act-pair · gpt-3.5-turbo

instances of the word "for" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DOWN

-0.71

soever

-0.67

alty

-0.66

properties

-0.66

lees

-0.65

mare

-0.65

leigh

-0.63

 THANK

-0.61

edin

-0.60

arios

-0.60

POSITIVE LOGITS

bidden

1.06

geries

0.94

gery

0.90

gotten

0.89

 hire

0.72

ays

0.72

 example

0.71

 instance

0.69

 starters

0.69

ked

0.68

Activations Density 0.116%

specific phrases indicating being tied or connected

instances of the word "for" in various contexts

No Comments

No Known Activations